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

    Neuronpedia

    INDEX
    Explanations

    game, who, even, live

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    들이
    0.44
    менти
    0.42
    TimeUnit
    0.40
     Benton
    0.40
    scalable
    0.40
     exemption
    0.39
    aidl
    0.39
     Lavinia
    0.39
     Breaks
    0.39
     giriş
    0.38
    POSITIVE LOGITS
    🇯
    0.52
     군
    0.48
    ugu
    0.47
    ău
    0.46
     দ
    0.45
    तुर
    0.44
    ច្
    0.44
    PAR
    0.44
    鄒
    0.44
     th
    0.42
    Act Density 0.000%

    No Known Activations