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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OnePlus
    0.89
     ʻ
    0.86
     Accenture
    0.85
     Einwill
    0.84
     Gmail
    0.82
     notificações
    0.81
     AstraZeneca
    0.80
     Ayuntamiento
    0.80
     Cortana
    0.80
     Usuario
    0.80
    POSITIVE LOGITS
     (\
    0.87
    frac
    0.84
     \
    0.83
    (\
    0.83
     -\
    0.77
    +\
    0.77
    geq
    0.75
    |_{
    0.75
    |\
    0.74
     $\
    0.74
    Act Density 0.041%

    No Known Activations