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

    Neuronpedia

    INDEX
    Explanations

    owning your identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ersk
    0.46
    ও
    0.46
    aino
    0.45
    gore
    0.45
    APPY
    0.45
     Moab
    0.44
     দু
    0.43
     উ
    0.43
    ResponseWriter
    0.43
    appy
    0.42
    POSITIVE LOGITS
     ಮಾಹಿತ
    0.48
     Specialties
    0.47
     ಸಮಸ್ಯೆ
    0.47
    ൨
    0.46
    情報
    0.45
     lettura
    0.43
    трі
    0.43
     utilizzo
    0.43
    鼕
    0.43
    現象
    0.42
    Act Density 0.002%

    No Known Activations