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

    Neuronpedia

    INDEX
    Explanations

    seed, children, dancing, phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }}-
    0.48
    әт
    0.48
     زیادی
    0.46
     Теннис
    0.44
     போ
    0.44
     जांच
    0.44
     ကျွန်
    0.44
     उन्नति
    0.43
     NDA
    0.42
     Everything
    0.42
    POSITIVE LOGITS
    in
    0.61
    s
    0.56
    3
    0.55
    ية
    0.53
    駙
    0.52
    o
    0.51
     flicks
    0.51
     in
    0.50
    del
    0.50
    ARI
    0.48
    Act Density 0.001%

    No Known Activations