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

    Neuronpedia

    INDEX
    Explanations

    considered so great

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    廃棄
    0.49
    ulfanyl
    0.47
    オン
    0.46
    Фу
    0.45
    ட்க
    0.45
    単
    0.44
    灏
    0.44
    Ῥ
    0.44
    𝗡
    0.44
     പിന്തുണ
    0.43
    POSITIVE LOGITS
     argues
    0.52
     Xbox
    0.45
     Wi
    0.44
     hates
    0.44
     almost
    0.43
     accused
    0.43
     so
    0.43
     cheerleader
    0.43
     comedy
    0.42
     arson
    0.42
    Act Density 0.009%

    No Known Activations