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

    Neuronpedia

    INDEX
    Explanations

    if conditional outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     youre
    1.06
    你在
    1.05
    你
    0.92
    你要
    0.91
    soever
    0.89
     আপনার
    0.86
     நீங்கள்
    0.85
     you
    0.85
     você
    0.85
    你有
    0.85
    POSITIVE LOGITS
     secondly
    0.68
    まさに
    0.68
     nejen
    0.67
    此外
    0.66
     במה
    0.64
     mutta
    0.64
    apses
    0.63
     wszystkim
    0.61
     hastily
    0.61
     continually
    0.60
    Act Density 0.015%

    No Known Activations