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

    Neuronpedia

    INDEX
    Explanations

    specific days and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     August
    0.51
     अगस्त
    0.49
     AUGUST
    0.47
     праздник
    0.47
     त्यौहार
    0.47
     celebration
    0.47
     празд
    0.47
     त्योहार
    0.47
     nation
    0.46
     tema
    0.46
    POSITIVE LOGITS
    riram
    0.45
     humiliation
    0.40
     decar
    0.39
     Yoshida
    0.36
     epiphany
    0.36
    Dec
    0.36
    extrem
    0.35
     decap
    0.35
    variants
    0.34
    Alchemy
    0.34
    Act Density 0.000%

    No Known Activations