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

    Neuronpedia

    INDEX
    Explanations

    called or labeled as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अर्थात
    0.99
    we
    0.95
     يعني
    0.89
     অর্থাৎ
    0.88
    योग्य
    0.86
     significa
    0.86
     более
    0.85
     यानी
    0.85
     signifie
    0.85
     connu
    0.84
    POSITIVE LOGITS
     misinformation
    0.87
     다양
    0.83
     quits
    0.83
    avoro
    0.82
     Opus
    0.81
    بدا
    0.80
     ADAM
    0.79
     multim
    0.79
    负责人
    0.78
    AlertDialog
    0.77
    Act Density 0.073%

    No Known Activations