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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ANDROID
    -0.06
    TL
    -0.06
     Nếu
    -0.06
    _save
    -0.06
    _PENDING
    -0.06
    楼
    -0.06
     Banc
    -0.06
     nullptr
    -0.06
     redundant
    -0.06
    .Resource
    -0.06
    POSITIVE LOGITS
     yytype
    0.08
    .distance
    0.07
    .↵↵↵↵
    0.07
    'R
    0.06
    |(↵
    0.06
    　ヾ
    0.06
    ellt
    0.06
    !).↵↵
    0.06
    μένοι
    0.06
    ....↵↵
    0.06
    Act Density 0.125%

    No Known Activations