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

    Neuronpedia

    INDEX
    Explanations

    time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     risky
    -0.06
    failed
    -0.06
    ?>↵
    -0.06
     alive
    -0.06
    _bits
    -0.06
     bad
    -0.06
    香蕉
    -0.06
    -0.06
     saja
    -0.06
    ゾ
    -0.06
    POSITIVE LOGITS
     rejo
    0.06
    .Bool
    0.06
     Fl
    0.06
    <uint
    0.06
     Flavor
    0.06
     Heb
    0.06
     cé
    0.06
     UserInfo
    0.06
     Χα
    0.06
     듣
    0.06
    Act Density 0.025%

    No Known Activations