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

    Neuronpedia

    INDEX
    Explanations

    change from start to end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lineales
    0.46
     theirs
    0.45
    ณิต
    0.45
     mathematic
    0.43
    ഞ്ചി
    0.43
     matemat
    0.42
     seater
    0.41
    னித
    0.41
     lipids
    0.41
     schnelle
    0.41
    POSITIVE LOGITS
     Starting
    0.57
    starting
    0.57
     starting
    0.57
     datap
    0.55
    Starting
    0.50
     recent
    0.47
     ending
    0.46
     Measurement
    0.43
     Recent
    0.43
    %,
    0.42
    Act Density 0.003%

    No Known Activations