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

    Neuronpedia

    INDEX
    Explanations

    cm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cockpit
    -0.06
    (candidate
    -0.06
     você
    -0.06
     Netz
    -0.06
    乾
    -0.06
    压
    -0.06
     hatta
    -0.06
    pass
    -0.06
     qualquer
    -0.06
     شر
    -0.06
    POSITIVE LOGITS
     pollut
    0.08
    ysical
    0.07
    _HERE
    0.07
    TableWidgetItem
    0.06
    _ANGLE
    0.06
    porate
    0.06
    params
    0.06
     없는
    0.06
    Plugin
    0.06
    _exceptions
    0.06
    Act Density 0.003%

    No Known Activations