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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mysql
    -0.07
     muht
    -0.06
    aná
    -0.06
    -k
    -0.06
     facult
    -0.06
     imagem
    -0.06
    assa
    -0.06
     города
    -0.06
     kre
    -0.06
     timeouts
    -0.06
    POSITIVE LOGITS
     Ivory
    0.06
     NSW
    0.06
     bağ
    0.06
     галуз
    0.06
     Pemb
    0.06
    ез
    0.05
     absolute
    0.05
     flavours
    0.05
     mám
    0.05
    SAN
    0.05
    Act Density 0.003%

    No Known Activations