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

    Neuronpedia

    INDEX
    Explanations

    along with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bra
    0.91
    Ks
    0.86
     си
    0.82
     operacional
    0.82
    LS
    0.81
    सिल
    0.81
     للح
    0.80
     onSuccess
    0.79
    asi
    0.78
    λι
    0.77
    POSITIVE LOGITS
    with
    2.01
     with
    1.91
     therewith
    1.74
     avec
    1.66
     với
    1.66
    WITH
    1.61
    dengan
    1.58
     withd
    1.57
     dengan
    1.54
    กับการ
    1.44
    Act Density 0.027%

    No Known Activations