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

    Neuronpedia

    INDEX
    Explanations

    positive exclamation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.64
    ів
    0.52
    ні
    0.46
    ام
    0.44
    on
    0.43
    िक
    0.43
    s
    0.43
    ის
    0.42
    ม
    0.41
    ات
    0.41
    POSITIVE LOGITS
     =)
    0.33
    {
    0.33
     indiquer
    0.33
     thiểu
    0.32
    ,(
    0.32
     auront
    0.31
    )(
    0.31
     =(
    0.31
    t
    0.31
    ,.
    0.30
    Act Density 0.079%

    No Known Activations