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

    Neuronpedia

    INDEX
    Explanations

    than factoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.49
     Britons
    0.47
    rne
    0.46
     stricter
    0.45
     exceptions
    0.44
     zunehm
    0.44
     случаев
    0.44
     lasciato
    0.43
    unless
    0.43
     inflexible
    0.43
    POSITIVE LOGITS
    avadoc
    0.52
    ونی
    0.49
    Wallet
    0.48
     প্রোগ্রাম
    0.48
     Wallet
    0.48
     briefing
    0.48
     Metaverse
    0.47
    jmp
    0.47
    วัง
    0.47
    開発
    0.47
    Act Density 0.049%

    No Known Activations