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

    Neuronpedia

    INDEX
    Explanations

    ns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    채
    -0.07
    潮
    -0.07
    聊
    -0.06
    $",
    -0.06
    (lr
    -0.06
     比
    -0.06
    _CREATE
    -0.06
    020
    -0.06
     GameObject
    -0.06
     Jes
    -0.06
    POSITIVE LOGITS
    toast
    0.06
     countdown
    0.06
     Gecko
    0.06
     babe
    0.06
    .CreateTable
    0.06
     planted
    0.06
     giveaway
    0.06
     Dat
    0.06
     finer
    0.06
    Mb
    0.06
    Act Density 0.003%

    No Known Activations