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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /media
    -0.06
    دة
    -0.06
    رة
    -0.06
     colossal
    -0.06
    _ENABLED
    -0.06
    جات
    -0.06
    _misc
    -0.06
    ああ
    -0.06
    λογή
    -0.06
    \AppData
    -0.06
    POSITIVE LOGITS
     LOSS
    0.08
     unless
    0.06
     sculpt
    0.06
     unpredictable
    0.06
    published
    0.06
    祥
    0.06
    葉
    0.06
    ++;↵
    0.06
    ï
    0.06
     GÜ
    0.06
    Act Density 0.024%

    No Known Activations