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

    Neuronpedia

    INDEX
    Explanations

    writing technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ượng
    0.41
    iciary
    0.41
    ު
    0.41
    火箭
    0.40
    ệm
    0.39
    iterator
    0.39
    imantan
    0.39
    ających
    0.38
    ễn
    0.37
    ICAGO
    0.37
    POSITIVE LOGITS
     pigments
    0.41
    괵
    0.40
    lera
    0.39
     काटे
    0.39
     Mortal
    0.39
    颉
    0.38
     dokument
    0.38
     adapta
    0.38
    Squad
    0.38
     adapted
    0.37
    Act Density 0.002%

    No Known Activations