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

    Neuronpedia

    INDEX
    Explanations

    returning data or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xiety
    0.46
    营养
    0.45
    γχ
    0.44
    మ్యాచ్
    0.43
    VEN
    0.43
    发育
    0.42
    Wend
    0.42
    0.42
    治疗
    0.42
    ≥
    0.41
    POSITIVE LOGITS
     result
    0.62
     data
    0.61
     results
    0.56
     return
    0.56
     info
    0.54
     returned
    0.52
     berupa
    0.52
     price
    0.51
     success
    0.50
     resultados
    0.50
    Act Density 0.196%

    No Known Activations