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

    Neuronpedia

    INDEX
    Explanations

    alphabetical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ༤
    0.52
    andaş
    0.51
    ທ່ານ
    0.50
    бил
    0.49
    ј
    0.49
    Ivoire
    0.49
    ối
    0.48
    меры
    0.48
    Информация
    0.48
    étend
    0.47
    POSITIVE LOGITS
     kiln
    0.51
     covers
    0.49
     essential
    0.48
     cover
    0.47
     kil
    0.46
     osmotic
    0.45
     choose
    0.45
     detailed
    0.44
     witch
    0.44
     continuous
    0.44
    Act Density 0.002%

    No Known Activations