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

    Neuronpedia

    INDEX
    Explanations

    numbers and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stessi
    0.79
     unconscious
    0.77
     panic
    0.77
    attere
    0.74
    უნქ
    0.74
     कोणत्या
    0.73
     esters
    0.73
    ELEASE
    0.73
     Panic
    0.72
    encript
    0.72
    POSITIVE LOGITS
    Хар
    0.79
    A
    0.64
    Sums
    0.64
    Er
    0.63
     sited
    0.62
     יד
    0.61
    heit
    0.61
    чер
    0.61
    ures
    0.60
    的机会
    0.59
    Act Density 0.000%

    No Known Activations