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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xbb
    -0.07
    洗礼
    -0.07
    fidf
    -0.07
    貔
    -0.07
    поз
    -0.06
    面前
    -0.06
    簉
    -0.06
     nộp
    -0.06
    developers
    -0.06
    פרופ
    -0.06
    POSITIVE LOGITS
     Little
    0.09
    _experiment
    0.08
    Little
    0.07
    𝐼
    0.07
     bart
    0.07
    APE
    0.07
    ⾷
    0.07
     .'
    0.07
    (sprintf
    0.07
     ................
    0.07
    Act Density 0.014%

    No Known Activations