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

    Neuronpedia

    INDEX
    Explanations

    grapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    но
    1.16
    сно
    1.16
    он
    1.06
    పై
    1.05
    лик
    1.05
     matemáticas
    1.05
    ول
    1.02
    тал
    1.02
     agrícolas
    1.02
    ној
    1.00
    POSITIVE LOGITS
     as
    1.41
            
    1.30
    e
    1.30
    ↵
    1.27
    AT
    1.20
     was
    1.20
     is
    1.16
    t
    1.16
     or
    1.15
    de
    1.13
    Act Density 0.002%

    No Known Activations