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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ФЛ
    -0.07
    unken
    -0.07
    bilder
    -0.07
    (hostname
    -0.07
    orna
    -0.07
    olo
    -0.07
     surname
    -0.07
     Cottage
    -0.07
    ITTE
    -0.07
     Sun
    -0.06
    POSITIVE LOGITS
     ReSharper
    0.06
     ﾊ
    0.06
     ej
    0.06
    ,)↵
    0.06
     lv
    0.06
     lends
    0.06
     hamburg
    0.06
    .BooleanField
    0.05
     INDIRECT
    0.05
     delighted
    0.05
    Act Density 0.008%

    No Known Activations