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

    Neuronpedia

    INDEX
    Explanations

    / expectation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лектро
    0.42
    ivalent
    0.40
     geval
    0.40
    ζα
    0.40
     invariably
    0.40
     tả
    0.40
    ammable
    0.39
     втор
    0.39
    颓
    0.39
    zaXRvcn
    0.38
    POSITIVE LOGITS
     M
    0.43
     Establish
    0.40
     ہوسکتا
    0.39
    リビング
    0.38
     Mount
    0.38
     Level
    0.38
     Nar
    0.37
     CPI
    0.37
     پشتی
    0.37
     Grant
    0.36
    Act Density 0.000%

    No Known Activations