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

    Neuronpedia

    INDEX
    Explanations

    might be able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essi
    0.48
     appunto
    0.44
     ursprüng
    0.42
     zelf
    0.41
     wodurch
    0.40
     roughly
    0.39
     seduced
    0.39
     drei
    0.38
     shaman
    0.38
     samot
    0.38
    POSITIVE LOGITS
     కూడా
    0.52
    也会
    0.50
    телям
    0.47
    かもしれませんが
    0.47
    बाबत
    0.47
    หาก
    0.47
     విషయంలో
    0.47
    에도
    0.46
    อาจ
    0.46
    거나
    0.46
    Act Density 0.000%

    No Known Activations