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

    Neuronpedia

    INDEX
    Explanations

    company reports, business, technical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     significantly
    0.42
     facilita
    0.40
     reconocida
    0.40
     basada
    0.39
    /
    0.39
    @
    0.39
    0.39
    flex
    0.38
     uniquely
    0.37
    na
    0.37
    POSITIVE LOGITS
    狲
    0.41
    荇
    0.41
    旄
    0.40
    MaxScaler
    0.40
    的时间
    0.40
    响
    0.40
    其余
    0.40
    ToSort
    0.39
    㚐
    0.38
    抔
    0.38
    Act Density 0.002%

    No Known Activations