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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🚥
    1.07
    🕚
    0.98
     gastronomy
    0.97
    🕔
    0.96
     frisch
    0.94
    🤚
    0.94
     funcionamiento
    0.94
    📙
    0.94
    🕓
    0.93
    🔃
    0.92
    POSITIVE LOGITS
    Jets
    0.85
    MeV
    0.78
    Year
    0.77
    Macrophages
    0.74
    Tr
    0.73
    I
    0.73
    ist
    0.72
    Max
    0.72
    beq
    0.72
    MAX
    0.71
    Act Density 0.012%

    No Known Activations