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

    Neuronpedia

    INDEX
    Explanations

    physical or digital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cass
    0.86
    Բ
    0.83
    䡓
    0.83
    ╽
    0.82
    تي
    0.81
    בער
    0.80
    zeniem
    0.80
     גע
    0.80
    ራሉ
    0.79
     trakcie
    0.78
    POSITIVE LOGITS
     basic
    0.70
     pr
    0.66
     gover
    0.63
     improve
    0.62
     पुस्तिका
    0.62
    sr
    0.61
     best
    0.61
     semblables
    0.61
     base
    0.60
     present
    0.60
    Act Density 0.001%

    No Known Activations