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

    Neuronpedia

    INDEX
    Explanations

    conceived as or by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.92
    refour
    0.86
    al
    0.86
    an
    0.85
    ти
    0.84
    aile
    0.81
    a
    0.80
    re
    0.79
    то
    0.79
    ol
    0.78
    POSITIVE LOGITS
    ↵
    0.82
     curriculum
    0.70
     conceived
    0.70
     Durango
    0.66
    器
    0.63
     chunk
    0.63
     preterm
    0.62
     $
    0.61
     DNA
    0.61
     sensor
    0.61
    Act Density 0.001%

    No Known Activations