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

    Neuronpedia

    INDEX
    Explanations

    story structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ANSI
    -0.08
     analy
    -0.07
    omo
    -0.07
    rogram
    -0.07
    وع
    -0.07
     completion
    -0.07
    alyze
    -0.07
     improved
    -0.07
     console
    -0.07
    bon
    -0.07
    POSITIVE LOGITS
     معرفی
    0.12
     കഥാപാത്ര
    0.10
     знакомства
    0.10
     protagonist
    0.10
    介紹
    0.10
    .Initialize
    0.10
    ーン
    0.10
     Einführung
    0.10
     personaje
    0.09
     meteen
    0.09
    Act Density 0.026%

    No Known Activations