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

    Neuronpedia

    INDEX
    Explanations

    probability calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emitter
    0.43
    ITECTURE
    0.43
    ELF
    0.41
     prona
    0.41
     capacitances
    0.39
    cellSize
    0.39
     sensores
    0.39
     شاف
    0.39
    當時
    0.38
    Khokhlov
    0.37
    POSITIVE LOGITS
     undefeated
    0.48
     winning
    0.48
     future
    0.45
     futurs
    0.42
    winning
    0.41
     rallies
    0.41
     മത്സര
    0.41
     winnings
    0.41
    future
    0.40
     Winning
    0.40
    Act Density 0.003%

    No Known Activations