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

    Neuronpedia

    INDEX
    Explanations

    110

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bethesda
    -0.07
     fearful
    -0.07
    esda
    -0.07
     soap
    -0.06
     Nancy
    -0.06
     fears
    -0.06
     Rei
    -0.06
    汇
    -0.06
     бой
    -0.06
     бух
    -0.06
    POSITIVE LOGITS
    110
    0.08
     Pack
    0.07
    440
    0.07
    ΟΦ
    0.07
    _DEST
    0.07
    220
    0.07
    err
    0.07
    109
    0.07
     Abbey
    0.06
     bibliography
    0.06
    Act Density 0.006%

    No Known Activations