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

    Neuronpedia

    INDEX
    Explanations

    brochures and pamphlets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Má
    0.41
     défi
    0.41
     пись
    0.39
     văn
    0.39
    ")->
    0.39
     Vans
    0.39
     الكسور
    0.39
     ur
    0.38
     ট্যাব
    0.38
     ডি
    0.37
    POSITIVE LOGITS
    pam
    0.55
     pamphlet
    0.51
     pamphlets
    0.50
     PAM
    0.49
    Pam
    0.47
     pam
    0.46
     കരുത
    0.44
     Pamph
    0.44
     pamph
    0.44
     storefront
    0.42
    Act Density 0.002%

    No Known Activations