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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    稆
    -0.07
     январ
    -0.07
    𝕦
    -0.07
    vell
    -0.07
    apk
    -0.07
    贷
    -0.07
    WWW
    -0.06
    ⬢
    -0.06
    挖
    -0.06
     adept
    -0.06
    POSITIVE LOGITS
    .writeString
    0.07
     bic
    0.07
    _SITE
    0.07
    isecond
    0.07
    مري
    0.06
     setMessage
    0.06
    .↵↵↵↵↵
    0.06
    [array
    0.06
    ConstraintMaker
    0.06
     pthread
    0.06
    Act Density 0.000%

    No Known Activations