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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dep
    0.49
    o
    0.48
    UK
    0.47
    4
    0.43
    E
    0.42
    dep
    0.42
    og
    0.42
    app
    0.41
     halogen
    0.41
    e
    0.41
    POSITIVE LOGITS
     单位
    0.48
    부터
    0.47
     Aralık
    0.46
    0.46
     خراب
    0.44
    ▛
    0.44
     Containing
    0.43
     يوليو
    0.42
    㝅
    0.42
     الصفحة
    0.41
    Act Density 0.018%

    No Known Activations