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

    Neuronpedia

    INDEX
    Explanations

    quoted or followed by connector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رو
    0.74
     bronze
    0.72
    𝗯
    0.72
    alike
    0.71
    pval
    0.70
     ljub
    0.70
    OLOGY
    0.69
    uncur
    0.68
     wal
    0.68
    كية
    0.68
    POSITIVE LOGITS
    haro
    0.71
     Eighty
    0.71
    !/"
    0.66
     Bagley
    0.65
    rtel
    0.64
     Dawson
    0.64
     пога
    0.63
    };\
    0.62
    полнение
    0.62
     unfavorable
    0.62
    Act Density 0.000%

    No Known Activations