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

    Neuronpedia

    INDEX
    Explanations

    Code/URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Если
    -0.08
     оз
    -0.06
    ,and
    -0.06
     Shea
    -0.06
    Draw
    -0.06
     FY
    -0.06
     misuse
    -0.05
     harus
    -0.05
     pleasing
    -0.05
    [strlen
    -0.05
    POSITIVE LOGITS
     접
    0.08
     redd
    0.07
    _EXPR
    0.07
     eğ
    0.07
     Vance
    0.07
    addTo
    0.07
    Opts
    0.06
    ++)
↵
    0.06
    associate
    0.06
    _BO
    0.06
    Act Density 0.000%

    No Known Activations