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

    Neuronpedia

    INDEX
    Explanations

    code blocks/imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roskop
    0.55
     flotation
    0.54
     is
    0.53
    a
    0.52
     are
    0.52
    3
    0.50
    льная
    0.49
     сохранить
    0.49
     ہوگا۔
    0.48
     retardation
    0.47
    POSITIVE LOGITS
    NG
    0.53
    مر
    0.53
    ecause
    0.50
    草
    0.50
    Z
    0.48
     Jank
    0.47
    ريك
    0.46
    ówki
    0.46
    जेक्ट
    0.45
     aiz
    0.45
    Act Density 0.000%

    No Known Activations