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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CC
    -0.08
    bitmap
    -0.07
    .fe
    -0.07
    三位
    -0.07
    $")↵
    -0.07
    仞
    -0.07
    btn
    -0.07
     infield
    -0.06
    Cube
    -0.06
     ngoài
    -0.06
    POSITIVE LOGITS
     создан
    0.07
    逃避
    0.07
    末端
    0.07
    瑕疵
    0.07
     airborne
    0.07
    屍
    0.07
     disappears
    0.07
     Siber
    0.06
    借口
    0.06
     embodied
    0.06
    Act Density 0.001%

    No Known Activations