Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    organizations/business

    np_max-act · gemini-2.0-flash

    technical specifications and descriptions related to electronic devices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is spot concrete object and component nouns (e.g. parts of devices, UI elements, technical “things”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .SEVERE
    -0.07
     verd
    -0.06
     vulnerabilities
    -0.06
    shiv
    -0.06
    ]|
    -0.06
    (result
    -0.06
    ldre
    -0.06
     interpersonal
    -0.06
     κυ
    -0.06
    .EventQueue
    -0.06
    POSITIVE LOGITS
    هدف
    0.07
    -winning
    0.07
     Rohing
    0.06
    ціон
    0.06
     تم
    0.06
    _An
    0.06
    Leon
    0.06
     تنظيف
    0.06
     Hilfe
    0.06
    ้าย
    0.06
    Act Density 0.310%

    No Known Activations