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

    Neuronpedia

    INDEX
    Explanations

    jacob and david

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ol
    0.64
    ט
    0.60
     ótimo
    0.60
    ură
    0.59
    year
    0.57
     básicas
    0.57
    科技
    0.56
    ost
    0.56
     godinu
    0.56
    培训
    0.55
    POSITIVE LOGITS
     در
    0.59
     식
    0.59
    :'#
    0.59
     با
    0.56
     Rebellion
    0.55
    ድን
    0.55
     때는
    0.54
    Rabbit
    0.54
     FIXED
    0.54
     だっ
    0.54
    Act Density 0.002%

    No Known Activations