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

    Neuronpedia

    INDEX
    Explanations

    that might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यूँ
    0.40
    punctuation
    0.37
    cular
    0.37
     രണ്ടു
    0.36
     আহম্মদ
    0.36
     Kahn
    0.36
     khan
    0.34
     হওয়ায়
    0.34
    aisesti
    0.34
    គឺជា
    0.33
    POSITIVE LOGITS
     hopefully
    0.73
    hopefully
    0.59
     phù
    0.55
     Hopefully
    0.54
    有助于
    0.53
     surpasses
    0.52
     possano
    0.50
    Hopefully
    0.50
     surpass
    0.49
     resonate
    0.49
    Act Density 0.009%

    No Known Activations