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

    Neuronpedia

    INDEX
    Explanations

    opening brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dž
    0.49
     оборудования
    0.46
     nari
    0.46
     calibrations
    0.43
     tans
    0.43
     संस्कार
    0.41
     neither
    0.41
     rokov
    0.40
     dá
    0.40
    slategray
    0.39
    POSITIVE LOGITS
    iorari
    0.39
    పో
    0.36
    TOTAL
    0.35
    ajout
    0.34
    foreground
    0.33
    余
    0.33
    Upcoming
    0.33
     लगाई
    0.32
    icier
    0.32
     forefront
    0.32
    Act Density 0.001%

    No Known Activations