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

    Neuronpedia

    INDEX
    Explanations

    ff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sniff
    -0.09
    삮
    -0.08
     vind
    -0.08
    돋
    -0.07
     erk
    -0.07
    лет
    -0.07
    ureen
    -0.07
     Gavin
    -0.07
    숲
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    .userid
    0.08
     iterations
    0.07
     Assumes
    0.07
    lotte
    0.07
     sqlite
    0.07
    полнить
    0.07
    Slash
    0.07
     IRA
    0.07
    RIORITY
    0.07
    ertation
    0.07
    Act Density 0.003%

    No Known Activations