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

    Neuronpedia

    INDEX
    Explanations

    and, or, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IZE
    0.49
    Assured
    0.48
    INSTALL
    0.46
     일반적으로
    0.46
    র
    0.46
    ELECT
    0.45
    Certification
    0.45
    México
    0.45
     kabupaten
    0.45
     типа
    0.45
    POSITIVE LOGITS
     and
    0.80
     ও
    0.70
     &
    0.68
     و
    0.63
    ！
    0.62
     व
    0.61
    及
    0.59
     и
    0.57
    !
    0.57
     et
    0.56
    Act Density 0.000%

    No Known Activations