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

    Neuronpedia

    INDEX
    Explanations

    title slide marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.48
    setVisible
    0.48
    ren
    0.47
    reader
    0.46
    wissenschaft
    0.46
    irnya
    0.45
    glyph
    0.45
     درباره
    0.44
    centralwidget
    0.44
    read
    0.44
    POSITIVE LOGITS
     slopes
    0.51
    我
    0.47
     hopes
    0.47
    适
    0.47
    啲
    0.46
    دأ
    0.46
     ہوگئی
    0.46
    觓
    0.45
    ácil
    0.44
     limiting
    0.44
    Act Density 0.000%

    No Known Activations