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

    Neuronpedia

    INDEX
    Explanations

    Q&A format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tilizers
    -0.78
     نمایید
    -0.78
    ):
    -0.77
    chafter
    -0.74
    бере
    -0.74
    lerden
    -0.73
     emocional
    -0.73
    ñó
    -0.73
    urar
    -0.72
    XIM
    -0.72
    POSITIVE LOGITS
     producto
    0.84
     vòng
    0.77
    くわ
    0.76
     Surveys
    0.76
     Bale
    0.74
     susc
    0.73
    榕
    0.73
    満足
    0.73
    createServer
    0.73
    ellem
    0.73
    Act Density 0.003%

    No Known Activations