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

    Neuronpedia

    INDEX
    Explanations

    PR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gerry
    0.45
     tradu
    0.41
    Bil
    0.40
     bil
    0.39
     Tours
    0.39
     torno
    0.38
     sed
    0.38
     identific
    0.37
     Translated
    0.37
     Madras
    0.37
    POSITIVE LOGITS
    лог
    0.46
     Nouvelle
    0.43
    houette
    0.42
     ಸಲ್ಲ
    0.41
    Nueva
    0.41
     submission
    0.41
     Corolle
    0.38
    னாக
    0.38
     outreach
    0.38
    скет
    0.37
    Act Density 0.005%

    No Known Activations