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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _update
    -0.07
     attempt
    -0.07
    ahoma
    -0.07
     prompts
    -0.07
     decl
    -0.07
    褲
    -0.07
    launch
    -0.07
     lazy
    -0.07
    不经
    -0.07
     Поэтому
    -0.07
    POSITIVE LOGITS
     обязан
    0.07
     Attachment
    0.06
    蘧
    0.06
    ution
    0.06
    锬
    0.06
    أوضاع
    0.06
    agment
    0.06
     lastIndex
    0.06
    أسواق
    0.06
    \xb
    0.06
    Act Density 0.018%

    No Known Activations