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

    Neuronpedia

    INDEX
    Explanations

    personality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -operation
    -0.07
     Encrypt
    -0.06
     Bulgaria
    -0.06
     getText
    -0.06
    シ
    -0.06
    ↵     ↵
    -0.06
     сви
    -0.06
     fiery
    -0.06
     moth
    -0.06
    ‌کن
    -0.06
    POSITIVE LOGITS
    NTAX
    0.06
    Payload
    0.06
    noun
    0.06
    _large
    0.06
     Engineer
    0.06
     arma
    0.06
     ostr
    0.06
     regardless
    0.06
    Arthur
    0.06
     eerie
    0.06
    Act Density 0.021%

    No Known Activations