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

    Neuronpedia

    INDEX
    Explanations

    several texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vous
    0.45
    embre
    0.44
    DOWN
    0.43
    endance
    0.42
    égale
    0.42
    em
    0.42
     subtracting
    0.42
     Evergreen
    0.41
    ch
    0.40
     प्लस
    0.40
    POSITIVE LOGITS
     시험
    0.47
     bör
    0.47
     압
    0.46
    อัล
    0.46
     zak
    0.46
     constru
    0.46
     inglesa
    0.46
     üt
    0.46
     analisar
    0.45
     oś
    0.45
    Act Density 0.000%

    No Known Activations