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

    Neuronpedia

    INDEX
    Explanations

    news snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _read
    -0.07
    Snapshot
    -0.07
    PIN
    -0.07
    :p
    -0.06
     autre
    -0.06
     controversial
    -0.06
    *cos
    -0.06
    �
    -0.06
    <|python_tag|>
    -0.06
    (widget
    -0.06
    POSITIVE LOGITS
     наг
    0.06
     člověka
    0.06
    Pizza
    0.06
     آقای
    0.06
     dissertation
    0.06
     NSStringFromClass
    0.06
    .populate
    0.06
    用
    0.06
     Namen
    0.06
     '''↵↵
    0.06
    Act Density 0.079%

    No Known Activations