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

    Neuronpedia

    INDEX
    Explanations

    php plugin headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \%
    0.37
    would
    0.36
    cyon
    0.36
    used
    0.35
    тельства
    0.34
    osomes
    0.34
     بالط
    0.34
     дана
    0.34
    </h3>
    0.33
    格子
    0.32
    POSITIVE LOGITS
    ჯგუფი
    0.42
     ది
    0.38
     アウター
    0.38
     waiver
    0.38
     lastname
    0.38
     giov
    0.38
    ﺅ
    0.37
     rif
    0.36
     Finger
    0.36
     hogi
    0.36
    Act Density 0.001%

    No Known Activations