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

    Neuronpedia

    INDEX
    Explanations

    half-life or approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ządu
    0.46
    ospor
    0.42
    フル
    0.40
     בדי
    0.39
     způ
    0.39
     Jaaye
    0.38
     ইপিআর
    0.38
     วัน
    0.38
     공식
    0.37
    ęła
    0.37
    POSITIVE LOGITS
     obwohl
    0.41
    rare
    0.38
    嘗
    0.38
     some
    0.38
     laminar
    0.38
     att
    0.38
     lâ
    0.38
    ieva
    0.37
     improve
    0.37
     overlapping
    0.37
    Act Density 0.000%

    No Known Activations