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

    Neuronpedia

    INDEX
    Explanations

    don't overdo it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    、【
    0.57
    ()}
    0.55
    }{}
    0.54
    築
    0.53
    QUIS
    0.53
    FREE
    0.53
    uskan
    0.52
     sco
    0.52
    ቋ
    0.52
    ίας
    0.52
    POSITIVE LOGITS
     Trabal
    0.66
    ઑ
    0.64
    giz
    0.64
    prec
    0.64
     până
    0.64
    بلا
    0.63
    ंजनों
    0.62
     பொ
    0.62
     refroidissement
    0.62
     کوتا
    0.62
    Act Density 0.144%

    No Known Activations