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

    Neuronpedia

    INDEX
    Explanations

    Software and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _redirect
    -0.08
    Ill
    -0.08
     alleg
    -0.07
     ill
    -0.07
     increment
    -0.07
    ibbon
    -0.07
    _chart
    -0.07
    continue
    -0.07
     Ill
    -0.07
    Blind
    -0.07
    POSITIVE LOGITS
    гөн
    0.08
     mús
    0.08
     Guin
    0.08
     матур
    0.08
     Diagnostics
    0.08
     guys
    0.08
     떠
    0.08
     –,
    0.08
    ګي
    0.08
    ګه
    0.08
    Act Density 0.146%

    No Known Activations