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

    Neuronpedia

    INDEX
    Explanations

    acronyms, definitions, what something means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    midnight
    0.49
     QuantityOnHand
    0.48
     낮
    0.45
    㣙
    0.45
     진
    0.45
     추
    0.43
     용
    0.43
     earthqu
    0.42
    ції
    0.41
     bày
    0.41
    POSITIVE LOGITS
    Мак
    0.48
     desempen
    0.48
    hObject
    0.43
     \
    0.42
    си
    0.42
    зде
    0.41
    де
    0.41
    з
    0.41
     mas
    0.41
     signific
    0.40
    Act Density 0.000%

    No Known Activations