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

    Neuronpedia

    INDEX
    Explanations

    dangerous enemies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     زینت
    0.52
     ecco
    0.50
    scopic
    0.48
     ممکن
    0.46
     れる
    0.46
     یعنی
    0.46
     riusc
    0.45
    ibility
    0.45
     ballad
    0.45
     dak
    0.44
    POSITIVE LOGITS
    h
    0.45
     ঐতিহ্য
    0.42
    கி
    0.41
    హ
    0.41
    Available
    0.41
     OUT
    0.40
     HOSPITAL
    0.40
    ร
    0.39
     Courses
    0.38
    ្រី
    0.38
    Act Density 0.002%

    No Known Activations