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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ese
    -0.07
    铯
    -0.07
    考古
    -0.07
    باس
    -0.07
    חמ
    -0.07
    כל
    -0.07
    _IMPL
    -0.07
    �
    -0.07
    锼
    -0.07
    otate
    -0.07
    POSITIVE LOGITS
     withdrawing
    0.06
    雅黑
    0.06
    hashed
    0.06
    为准
    0.06
     gratuita
    0.06
    残忍
    0.06
    上榜
    0.06
     '_
    0.06
     relev
    0.06
    ');
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations