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

    Neuronpedia

    INDEX
    Explanations

    academic publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pripad
    0.41
     Luís
    0.39
    ovas
    0.39
    વેશ
    0.38
     physiology
    0.38
     logarithm
    0.38
     Artur
    0.38
     traceability
    0.37
     इमर
    0.37
     Neymar
    0.37
    POSITIVE LOGITS
     London
    0.70
     Toronto
    0.63
     Minneapolis
    0.61
     Londres
    0.61
     Oxford
    0.61
    London
    0.61
    Toronto
    0.60
     Chicago
    0.57
     Honolulu
    0.57
     Londra
    0.57
    Act Density 0.004%

    No Known Activations