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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hab
    -0.06
    Otherwise
    -0.06
     Otherwise
    -0.06
     몽
    -0.06
    Every
    -0.05
    uring
    -0.05
    ्द
    -0.05
    Consult
    -0.05
    Нас
    -0.05
     Every
    -0.05
    POSITIVE LOGITS
    ategorias
    0.07
    ]).
    0.07
    leine
    0.07
    exampleModal
    0.07
    NoSuch
    0.07
    ,proto
    0.07
     Вели
    0.07
     centralized
    0.07
    kiye
    0.07
    Jim
    0.07
    Act Density 0.001%

    No Known Activations