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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amnesty
    -0.07
     Meadows
    -0.07
    為了
    -0.07
     zobowiąz
    -0.07
     Telephone
    -0.07
    兆
    -0.06
     Schön
    -0.06
     costa
    -0.06
    ぎ
    -0.06
     cumshot
    -0.06
    POSITIVE LOGITS
    ODEV
    0.08
    AndView
    0.07
    RAR
    0.07
    _cuda
    0.07
     Independent
    0.07
    '))↵↵
    0.07
    彰显
    0.07
    [layer
    0.07
    阐述
    0.07
    を中心
    0.07
    Act Density 0.010%

    No Known Activations