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

    Neuronpedia

    INDEX
    Explanations

    around quoted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ત્મક
    0.62
     използва
    0.60
    گر
    0.58
     ልዩ
    0.57
     assaulted
    0.56
     elevationMap
    0.55
     khususnya
    0.55
     figuratively
    0.55
    මු
    0.54
     zealous
    0.54
    POSITIVE LOGITS
    plotlib
    0.46
    routes
    0.45
    JobID
    0.45
    lda
    0.45
     DEALINGS
    0.43
    ην
    0.42
    synth
    0.41
    sia
    0.41
     combustibles
    0.40
    package
    0.40
    Act Density 0.000%

    No Known Activations