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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    論
    -0.08
     Clinic
    -0.07
    搖
    -0.07
    ར
    -0.07
    w
    -0.07
    微观
    -0.07
    独立董事
    -0.07
    TokenType
    -0.07
    မ
    -0.06
     Stars
    -0.06
    POSITIVE LOGITS
     =>{↵
    0.08
    >E
    0.07
    >A
    0.07
     Чтобы
    0.07
    >";
    0.07
     받아
    0.07
    ❓
    0.07
     hed
    0.07
    prevent
    0.07
     Happiness
    0.06
    Act Density 0.140%

    No Known Activations