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

    Neuronpedia

    INDEX
    Explanations

    involves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOGGER
    -0.07
    鼓
    -0.06
    olit
    -0.06
    雅
    -0.06
     nedeniyle
    -0.06
     orders
    -0.06
    爾
    -0.06
    _team
    -0.06
    SITE
    -0.06
     Calc
    -0.06
    POSITIVE LOGITS
    aversable
    0.08
     urlencode
    0.06
     Chronicles
    0.06
    Scores
    0.06
    _pedido
    0.06
    &id
    0.06
     pacman
    0.06
    _VERIFY
    0.06
    Missing
    0.06
     μέ
    0.06
    Act Density 0.020%

    No Known Activations