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

    Neuronpedia

    INDEX
    Explanations

    say "font"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Miss
    -0.07
     My
    -0.07
     {?
    -0.07
     Pee
    -0.07
    strtolower
    -0.07
    egrate
    -0.06
     حيات
    -0.06
     objeto
    -0.06
     dismissing
    -0.06
    /documentation
    -0.06
    POSITIVE LOGITS
    -fed
    0.07
    ');↵
    0.07
    '}>↵
    0.07
    _API
    0.07
    (Stack
    0.07
    Shares
    0.07
    剧情
    0.07
    集聚
    0.07
     interrupt
    0.07
    ccount
    0.07
    Act Density 0.001%

    No Known Activations