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

    Neuronpedia

    INDEX
    Explanations

    similar to but with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ignation
    0.54
     Pharaoh
    0.51
     سایټ
    0.50
    伉
    0.50
    hitung
    0.50
    if
    0.49
     ترجم
    0.49
     જાણી
    0.49
    sadpoetry
    0.49
    pyrazole
    0.48
    POSITIVE LOGITS
     da
    0.55
     nélkül
    0.53
     with
    0.51
     +
    0.51
     dart
    0.51
     tonal
    0.49
     lessened
    0.49
     예
    0.48
     sólo
    0.48
     gering
    0.47
    Act Density 0.077%

    No Known Activations