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

    Neuronpedia

    INDEX
    Explanations

    skill description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    让你
    0.42
     sustancia
    0.41
     bakım
    0.40
    και
    0.38
    弋
    0.38
    нили
    0.37
     reforma
    0.37
    奢
    0.37
    villa
    0.37
     gratuita
    0.36
    POSITIVE LOGITS
    ಿಯನ್ನು
    0.42
     footnote
    0.42
     Caption
    0.40
     چې
    0.39
     Preface
    0.38
     heading
    0.37
     relatively
    0.36
     potato
    0.36
     footnotes
    0.36
    少なくとも
    0.36
    Act Density 0.000%

    No Known Activations