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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Renderer
    -0.06
    .ReadOnly
    -0.06
    _qty
    -0.06
     груп
    -0.06
    -pencil
    -0.06
    (widget
    -0.06
    ."]
    -0.05
    ulmuş
    -0.05
     uprising
    -0.05
    _detalle
    -0.05
    POSITIVE LOGITS
     gym
    0.08
    IT
    0.07
    _play
    0.07
    ated
    0.07
    _act
    0.07
     Nes
    0.06
    ючись
    0.06
    DELETE
    0.06
    972
    0.06
     params
    0.06
    Act Density 0.000%

    No Known Activations