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

    Neuronpedia

    INDEX
    Explanations

    navigating two distinct areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.54
     and
    0.46
     declared
    0.43
    咎
    0.41
     declare
    0.41
     Communications
    0.41
    declaration
    0.40
     That
    0.40
    cephalus
    0.40
    וב
    0.39
    POSITIVE LOGITS
    pekte
    0.47
    َّا
    0.46
    漅
    0.45
    可能會
    0.45
    čiť
    0.44
     طرق
    0.44
    詼
    0.44
    诙
    0.43
    imcoords
    0.42
    मॉ
    0.42
    Act Density 0.001%

    No Known Activations