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

    Neuronpedia

    INDEX
    Explanations

    causation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Passport
    -0.08
     الفني
    -0.08
    -disc
    -0.08
     उस
    -0.08
     שלך
    -0.07
     שלי
    -0.07
     الفنية
    -0.07
    في
    -0.07
     المصدر
    -0.07
     gén
    -0.07
    POSITIVE LOGITS
     negligible
    0.09
     watches
    0.08
     remembering
    0.08
     strives
    0.08
     aiming
    0.08
     cares
    0.08
     noting
    0.08
     independ
    0.07
     lembr
    0.07
    oners
    0.07
    Act Density 0.023%

    No Known Activations