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

    Neuronpedia

    INDEX
    Explanations

    architectural styles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getStatus
    -0.07
     Dünya
    -0.07
     tür
    -0.06
     dolls
    -0.06
     plates
    -0.06
     signal
    -0.06
     Julius
    -0.06
     syn
    -0.06
     уровня
    -0.06
     zombies
    -0.06
    POSITIVE LOGITS
    してい
    0.07
    __()↵
    0.07
    //------------------------------------------------------------------------------↵↵
    0.06
     دادن
    0.06
     ")↵↵
    0.06
     antic
    0.06
     —
    0.06
     --------------------------------------------------------------------------↵
    0.06
     '''
↵
    0.06
     •
    0.06
    Act Density 0.009%

    No Known Activations