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

    Neuronpedia

    INDEX
    Explanations

    science programs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Damages
    0.69
    Kons
    0.65
    Dados
    0.63
    ບໍ
    0.61
    phasis
    0.61
    alat
    0.60
     dritten
    0.60
     للمع
    0.59
     Wages
    0.59
    伝説
    0.59
    POSITIVE LOGITS
     science
    0.61
     giorno
    0.59
     natural
    0.57
     anchor
    0.56
    eball
    0.56
     programs
    0.55
     {\
    0.55
     proxy
    0.55
    ier
    0.54
     (\
    0.54
    Act Density 0.000%

    No Known Activations