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

    Neuronpedia

    INDEX
    Explanations

    E or E2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    legt
    0.54
    avljen
    0.52
    ardı
    0.50
     ਉਸ
    0.48
    akt
    0.48
    ک
    0.46
    اعد
    0.46
     പതി
    0.46
    ētu
    0.46
     सीकर
    0.44
    POSITIVE LOGITS
     across
    0.57
     ergonomic
    0.55
     guarantee
    0.54
     four
    0.51
     avanc
    0.51
     isos
    0.51
     triang
    0.50
     quote
    0.50
     impasse
    0.50
     shares
    0.49
    Act Density 0.000%

    No Known Activations