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

    Neuronpedia

    INDEX
    Explanations

    greetings and apologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.85
    an
    0.82
    eine
    0.77
     والإ
    0.74
     възможно
    0.74
    े
    0.73
    ра
    0.70
    is
    0.69
     StringIO
    0.67
    е
    0.65
    POSITIVE LOGITS
    enance
    0.73
    ствие
    0.70
    etically
    0.66
    atge
    0.66
     linestyle
    0.66
    ्स
    0.66
     gian
    0.65
    Transforms
    0.65
    lessly
    0.65
    🙏🙏
    0.64
    Act Density 0.319%

    No Known Activations