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

    Neuronpedia

    INDEX
    Explanations

    technical and non-english scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нула
    0.52
    Ladder
    0.50
    ους
    0.48
    Countdown
    0.47
     Лу
    0.47
     （
    0.46
    ATIC
    0.46
    TN
    0.46
     snowboard
    0.46
     binge
    0.45
    POSITIVE LOGITS
    ب
    0.44
     Textbook
    0.40
    that
    0.39
    અ
    0.39
    ígenes
    0.38
    portional
    0.38
     recordemos
    0.38
    renti
    0.38
    ちは
    0.38
     customary
    0.38
    Act Density 0.003%

    No Known Activations