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

    Neuronpedia

    INDEX
    Explanations

    understanding your needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رب
    0.44
     ياس
    0.44
     sprinkles
    0.43
    յան
    0.42
    gruntled
    0.42
    zt
    0.41
     العديد
    0.41
    Many
    0.40
     تأثير
    0.40
    匾
    0.40
    POSITIVE LOGITS
    旖
    0.45
     unser
    0.44
     оба
    0.44
     режима
    0.44
    Α
    0.43
     оконча
    0.43
     کجا
    0.42
     роди
    0.42
     реша
    0.42
     we
    0.41
    Act Density 0.000%

    No Known Activations