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

    Neuronpedia

    INDEX
    Explanations

    _modules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _curve
    -0.07
     Fin
    -0.07
     الشي
    -0.06
     民
    -0.06
    xn
    -0.06
     fout
    -0.06
    按钮
    -0.06
     wizard
    -0.06
    /sql
    -0.06
     locale
    -0.06
    POSITIVE LOGITS
    _modules
    0.08
     ngoài
    0.07
     lets
    0.06
     instantaneous
    0.06
    (previous
    0.06
    омет
    0.06
    _PLUGIN
    0.06
    _MORE
    0.06
    ],$
    0.06
    蜘蛛词
    0.06
    Act Density 0.001%

    No Known Activations