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

    Neuronpedia

    INDEX
    Explanations

    latex environments and packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ङ
    0.35
    ARY
    0.34
    ़
    0.34
    人形
    0.33
     Anas
    0.33
    Missense
    0.33
    पेयी
    0.33
    STANDING
    0.33
    اي
    0.33
     девушка
    0.33
    POSITIVE LOGITS
    {}{
    0.41
     {
    0.40
    oustache
    0.39
    {}
    0.37
    {
    0.37
    *{
    0.36
    {!
    0.36
     set
    0.35
     {(
    0.34
    {(
    0.34
    Act Density 0.001%

    No Known Activations