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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NAS
    -0.08
    了一个
    -0.07
     constitution
    -0.07
     Junior
    -0.07
     pipe
    -0.07
    Operator
    -0.07
    疑
    -0.07
    级
    -0.06
     mContext
    -0.06
     electr
    -0.06
    POSITIVE LOGITS
     winnings
    0.07
    鬏
    0.07
    𝑊
    0.06
     להשיג
    0.06
     sidew
    0.06
    换取
    0.06
    쏴
    0.06
    몃
    0.06
     znaleźć
    0.06
    活得
    0.06
    Act Density 0.002%

    No Known Activations