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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    technical descriptions related to optical systems and imaging technologies.

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

    This neuron detects numeric measurement tokens, especially floating-point numbers and units in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    objects
    -0.07
    alone
    -0.06
     achieved
    -0.06
    empl
    -0.06
     pins
    -0.06
    Ion
    -0.06
     boxing
    -0.06
    Those
    -0.06
     ship
    -0.06
     CPU
    -0.06
    POSITIVE LOGITS
    .stub
    0.07
    .InnerText
    0.07
    .XRLabel
    0.07
     uží
    0.06
    西省
    0.06
     Kanunu
    0.06
     ('$
    0.06
     표
    0.06
     "'");↵
    0.06
    .TRAN
    0.06
    Act Density 0.014%

    No Known Activations