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

    Neuronpedia

    INDEX
    Explanations

    ivers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    פך
    -0.07
    ثقافة
    -0.07
    เก
    -0.07
    ocê
    -0.06
    owości
    -0.06
    .addCell
    -0.06
     stif
    -0.06
    芜
    -0.06
    쭉
    -0.06
    _misc
    -0.06
    POSITIVE LOGITS
     Amanda
    0.08
     hj
    0.07
    landırma
    0.07
    manda
    0.07
    化妆品
    0.07
     Amy
    0.07
    Aj
    0.07
     rotate
    0.07
    *j
    0.06
    렜
    0.06
    Act Density 0.009%

    No Known Activations