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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cer
    -0.07
    凌
    -0.06
     Rug
    -0.06
    Collection
    -0.06
    "}
    -0.06
    _STRING
    -0.06
     shr
    -0.06
     referred
    -0.06
    $total
    -0.06
    Anthony
    -0.06
    POSITIVE LOGITS
    люд
    0.07
     Navigate
    0.07
    ﾏ
    0.07
    욕
    0.06
    occup
    0.06
    istinguish
    0.06
    !:
    0.06
     unus
    0.06
    ัต
    0.06
    AFX
    0.06
    Act Density 0.013%

    No Known Activations