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

    Neuronpedia

    INDEX
    Explanations

    software settings/errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.06
     asympt
    -0.06
     Hera
    -0.06
    ятно
    -0.06
    �
    -0.06
    .Clamp
    -0.06
    summ
    -0.06
    bearing
    -0.06
    -bearing
    -0.06
     GIF
    -0.06
    POSITIVE LOGITS
     рань
    0.07
     rien
    0.07
     Jab
    0.07
    .unknown
    0.07
    ñ
    0.07
     DISPLAY
    0.06
    …
    0.06
     наблюд
    0.06
     Genç
    0.06
    Always
    0.06
    Act Density 0.055%

    No Known Activations