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

    Neuronpedia

    INDEX
    Explanations

    further detail on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    數量
    0.45
    レーター
    0.38
    ングル
    0.38
    upar
    0.37
    Стра
    0.37
    ਸ਼ਨ
    0.37
    統合
    0.37
    acuda
    0.37
    危機
    0.36
    উজ
    0.36
    POSITIVE LOGITS
     thermodynam
    0.48
     lambs
    0.47
     erred
    0.46
     assassinated
    0.46
     beef
    0.46
     drenched
    0.46
     wept
    0.45
     raged
    0.45
     pelle
    0.45
     pegged
    0.45
    Act Density 0.001%

    No Known Activations