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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash

    code-related terms and concepts in software development.

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

    The neuron activates on version‐control metadata, especially revision/ID numbers and related annotations in comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    职业
    -0.07
    Clr
    -0.07
    iaz
    -0.07
     singer
    -0.07
     FAIL
    -0.07
     تجاری
    -0.07
    _SN
    -0.07
     гр
    -0.06
     قابلیت
    -0.06
    βέρ
    -0.06
    POSITIVE LOGITS
     đứ
    0.06
     POSIX
    0.06
    磨
    0.06
    Keith
    0.06
     dinosaurs
    0.06
    .padding
    0.05
    uild
    0.05
     Setup
    0.05
    ck
    0.05
    าหล
    0.05
    Act Density 0.001%

    No Known Activations