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

    Neuronpedia

    INDEX
    Explanations

    flashcards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    名の
    0.46
    Session
    0.46
    phi
    0.45
    ИА
    0.45
     viscous
    0.44
    hea
    0.43
    php
    0.43
    Name
    0.43
     न
    0.42
     جوس
    0.42
    POSITIVE LOGITS
     要素
    0.62
     Unternehmer
    0.61
     Einf
    0.57
    ي
    0.57
     Empresas
    0.56
     staat
    0.55
     oleks
    0.55
    ES
    0.55
     toneladas
    0.54
     Vereins
    0.54
    Act Density 0.010%

    No Known Activations