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

    Neuronpedia

    INDEX
    Explanations

    ordinary, extraordinary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stencil
    -0.08
     slapped
    -0.07
     butter
    -0.07
    13
    -0.07
     Pang
    -0.06
    _BYTE
    -0.06
    Align
    -0.06
     Salad
    -0.06
    aniem
    -0.06
     Butter
    -0.06
    POSITIVE LOGITS
     extraordin
    0.07
     abnormal
    0.07
     extraordinary
    0.07
    ophon
    0.07
     generosity
    0.07
    FunctionFlags
    0.06
     الخاص
    0.06
    :false
    0.06
    _some
    0.06
     misconduct
    0.06
    Act Density 0.039%

    No Known Activations