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

    Neuronpedia

    INDEX
    Explanations

    disclaimer:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    0.80
    𝒶
    0.76
    QT
    0.76
     UEFI
    0.76
    OBJ
    0.76
     petitioned
    0.75
    𝓊
    0.73
     strange
    0.73
    entions
    0.72
     mist
    0.72
    POSITIVE LOGITS
     aceasta
    0.93
     világ
    0.89
    дных
    0.87
     निकला
    0.87
     disclaimer
    0.86
     değildir
    0.86
    注意
    0.85
     निकल
    0.85
    我知道
    0.84
    owanych
    0.84
    Act Density 0.009%

    No Known Activations