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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extensão
    0.72
    㗁
    0.71
    hyperref
    0.71
     chrys
    0.69
    សំណ
    0.69
     வெளிப்புற
    0.69
    blonde
    0.68
     lordship
    0.68
     deuteron
    0.68
    الله
    0.68
    POSITIVE LOGITS
     absolute
    0.73
     absolutely
    0.71
    formen
    0.69
     तला
    0.67
     relative
    0.67
     절대
    0.65
    fixed
    0.64
     πα
    0.62
     fixed
    0.61
     Absolute
    0.61
    Act Density 0.005%

    No Known Activations