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

    Neuronpedia

    INDEX
    Explanations

    portfolio breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     справи
    0.47
     verificar
    0.46
     kiểm
    0.46
     eventuali
    0.44
     yardımcı
    0.44
     verhindert
    0.44
     sağlam
    0.43
     partire
    0.43
    Parte
    0.43
     investigar
    0.42
    POSITIVE LOGITS
     connotation
    0.47
     ক্রিকে
    0.44
    選択
    0.41
     racial
    0.40
    摒
    0.40
     Patreon
    0.39
     Schur
    0.39
     Capitalism
    0.39
     Tired
    0.39
     ধরন
    0.38
    Act Density 0.007%

    No Known Activations