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

    Neuronpedia

    INDEX
    Explanations

    absence or singularity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     B
    0.66
     ALSO
    0.62
     devrez
    0.59
     they
    0.58
     PLUS
    0.58
     DIRE
    0.57
     X
    0.55
     SOME
    0.55
     GRAY
    0.54
     WHILE
    0.54
    POSITIVE LOGITS
    as
    0.76
    任何
    0.68
    SDK
    0.66
     எந்த
    0.61
     没有
    0.59
    BetMap
    0.57
    odată
    0.56
    或
    0.56
    új
    0.55
     或
    0.55
    Act Density 0.406%

    No Known Activations