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

    Neuronpedia

    INDEX
    Explanations

    and | followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এখানে
    0.41
    খানে
    0.37
     queste
    0.35
     autori
    0.35
     mors
    0.34
     পুঁ
    0.34
     canzone
    0.33
     neste
    0.33
     aquí
    0.32
     هنا
    0.32
    POSITIVE LOGITS
    {
    0.46
    (
    0.40
    f
    0.39
     of
    0.39
    지
    0.37
    m
    0.34
    도
    0.34
    ين
    0.33
     a
    0.33
    কে
    0.33
    Act Density 0.633%

    No Known Activations