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

    Neuronpedia

    INDEX
    Explanations

    well- or widely- + accepted/documented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Done
    0.50
     talented
    0.43
     அமைந்துள்ளது
    0.41
    Done
    0.40
     reputable
    0.40
     ünlü
    0.39
     yapmış
    0.38
     famous
    0.38
     असून
    0.38
    醎
    0.38
    POSITIVE LOGITS
    documented
    0.60
     rehears
    0.57
     documented
    0.56
    explored
    0.55
    reported
    0.54
    accepted
    0.54
     held
    0.51
    held
    0.51
     studied
    0.50
     accepted
    0.50
    Act Density 0.023%

    No Known Activations