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

    Neuronpedia

    INDEX
    Explanations

    creative text generation, code, translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    predictor
    0.37
     xrange
    0.36
    ذك
    0.34
    tablet
    0.34
    raphe
    0.33
     quantifier
    0.32
     badge
    0.32
    Ov
    0.31
     ray
    0.31
    gesture
    0.30
    POSITIVE LOGITS
     अनुवाद
    0.53
     translations
    0.52
     Translation
    0.51
     translation
    0.50
     অনুবাদ
    0.50
     Translations
    0.49
    翻譯
    0.47
    翻訳
    0.47
    翻译
    0.46
    コード
    0.45
    Act Density 0.063%

    No Known Activations