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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash

    This neuron activates on phone‐number components (digits and related punctuation), detecting contact phone numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    san
    -0.07
    BI
    -0.06
     director
    -0.06
     Directors
    -0.06
    _a
    -0.06
     decis
    -0.06
     prohibited
    -0.06
    proved
    -0.06
     Extras
    -0.06
    asan
    -0.06
    POSITIVE LOGITS
    PointCloud
    0.07
    』↵↵
    0.06
     مذه
    0.06
    nite
    0.06
     __('
    0.06
     postId
    0.06
    DoubleClick
    0.06
    (rt
    0.06
    `,`
    0.06
    .Unlock
    0.06
    Act Density 0.011%

    No Known Activations