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

    Neuronpedia

    INDEX
    Explanations

    evaluate answer or threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    زر
    0.46
    子
    0.44
    pled
    0.43
    ുകളെ
    0.43
    गुड
    0.42
    weni
    0.42
    يتها
    0.41
     parro
    0.41
    pupp
    0.41
    دت
    0.41
    POSITIVE LOGITS
     farther
    0.59
     graduates
    0.52
     magazine
    0.46
     chops
    0.45
     dashed
    0.44
     chefs
    0.44
     paradox
    0.44
     parallel
    0.44
     تجربه
    0.44
     hybrid
    0.44
    Act Density 0.034%

    No Known Activations