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

    Neuronpedia

    INDEX
    Explanations

    command line grep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    简介
    0.32
    ě
    0.30
    预
    0.30
     মনোরম
    0.29
     foarte
    0.29
    р
    0.29
    农
    0.29
     надеюсь
    0.29
     encouraging
    0.29
     খুবই
    0.29
    POSITIVE LOGITS
     disequ
    0.31
    餾
    0.29
     the
    0.28
     genders
    0.28
    consumed
    0.28
    りの
    0.27
    含量
    0.27
     ভোগের
    0.27
    Consumed
    0.27
     Liye
    0.26
    Act Density 0.000%

    No Known Activations