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

    Neuronpedia

    INDEX
    Explanations

    control mechanisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dx
    -0.08
    izza
    -0.07
     abortion
    -0.07
     gay
    -0.07
    Ping
    -0.07
     Israel
    -0.07
     yoga
    -0.07
     caldo
    -0.07
     matrimonio
    -0.07
    kommun
    -0.07
    POSITIVE LOGITS
    按钮
    0.12
    钮
    0.12
     переключ
    0.12
     knobs
    0.11
     кноп
    0.11
     bediening
    0.11
     кнопку
    0.11
     movable
    0.11
     knob
    0.10
    /buttons
    0.10
    Act Density 0.036%

    No Known Activations