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

    Neuronpedia

    INDEX
    Explanations

    see all photos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elucidation
    0.45
     tumult
    0.43
     hypersur
    0.42
     bened
    0.42
     stunned
    0.42
    bius
    0.41
     bison
    0.40
     administration
    0.39
     artis
    0.39
     partis
    0.39
    POSITIVE LOGITS
    Sach
    0.42
    贍
    0.42
     Scoring
    0.41
     ترین
    0.40
     Voir
    0.39
     हो
    0.39
    𝐼
    0.38
    ेड
    0.38
    مكن
    0.38
     І
    0.37
    Act Density 0.000%

    No Known Activations