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

    Neuronpedia

    INDEX
    Explanations

    numbers and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    宾
    0.54
    enza
    0.48
    Calibration
    0.47
     బ
    0.45
    Kabhi
    0.44
    वणी
    0.44
    循环
    0.43
    setBackground
    0.43
    ند
    0.43
    賓
    0.43
    POSITIVE LOGITS
     disponibles
    0.60
     entrants
    0.57
     obscures
    0.57
     available
    0.55
     patents
    0.55
     opposes
    0.54
     bets
    0.54
     disponíveis
    0.54
     gamers
    0.53
     heats
    0.53
    Act Density 0.199%

    No Known Activations