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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Vector
    -0.08
     History
    -0.07
    etAddress
    -0.06
    淄
    -0.06
     skulle
    -0.06
     deploy
    -0.06
    bsite
    -0.06
     Kitt
    -0.06
    -billion
    -0.06
    Zip
    -0.06
    POSITIVE LOGITS
     avaliações
    0.07
     métier
    0.07
    '][]
    0.07
     likes
    0.07
    пус
    0.07
    🚿
    0.06
    펄
    0.06
     Rencontres
    0.06
     bước
    0.06
    walker
    0.06
    Act Density 0.033%

    No Known Activations