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

    Neuronpedia

    INDEX
    Explanations

    starts with code or markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ரியில்
    0.42
     राज्यपाल
    0.39
    rekt
    0.38
    HWND
    0.38
    govt
    0.38
    breakfast
    0.37
    آپ
    0.37
    бия
    0.37
    SOME
    0.36
    𝟬
    0.36
    POSITIVE LOGITS
     Comes
    0.40
     Forbidden
    0.38
    ืม
    0.38
    comes
    0.37
    ilihan
    0.36
     kick
    0.36
     "
    0.35
    uva
    0.35
     ^{
    0.35
    opens
    0.35
    Act Density 0.000%

    No Known Activations