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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wholly
    -0.07
    航母
    -0.07
    _TRANSACTION
    -0.07
     naval
    -0.07
    @Component
    -0.07
     relent
    -0.07
     Button
    -0.07
    lien
    -0.07
    货币
    -0.07
    _wrapper
    -0.06
    POSITIVE LOGITS
     Prom
    0.07
     kötü
    0.07
     alta
    0.07
    前
    0.07
     "\\
    0.07
    找到了
    0.07
    fullscreen
    0.07
    并不能
    0.06
    tek
    0.06
    izione
    0.06
    Act Density 0.062%

    No Known Activations