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

    Neuronpedia

    INDEX
    Explanations

    challenge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Minuten
    -0.08
     fueron
    -0.07
    ot
    -0.07
    peat
    -0.07
     görül
    -0.07
    感到
    -0.07
     Typical
    -0.07
     Superior
    -0.07
     Woodward
    -0.07
     ücretsiz
    -0.07
    POSITIVE LOGITS
     Bal
    0.07
    �
    0.07
    .Dev
    0.06
    _contr
    0.06
     Att
    0.06
     {});↵↵
    0.06
    (span
    0.06
    ,Th
    0.06
    ض
    0.06
    ‌المللی
    0.06
    Act Density 0.007%

    No Known Activations