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

    Neuronpedia

    INDEX
    Explanations

    computational concepts or coding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Error
    0.44
     ERROR
    0.43
     fmt
    0.43
     erro
    0.40
    error
    0.40
     Errors
    0.39
    getError
    0.39
     error
    0.39
     WALL
    0.39
     OPEN
    0.38
    POSITIVE LOGITS
    дяки
    0.46
    uchtigkeit
    0.40
    ськ
    0.39
     kunst
    0.39
    বার্গ
    0.39
     ወይም
    0.39
     добав
    0.39
     Kabupaten
    0.38
     artificielle
    0.38
    בק
    0.38
    Act Density 0.000%

    No Known Activations