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

    Neuronpedia

    INDEX
    Explanations

    fixed or predictable information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ص
    0.40
    і
    0.39
    مص
    0.39
    缺
    0.38
     zelfs
    0.36
    ᱑
    0.35
    的基本
    0.35
     домаш
    0.35
    اج
    0.35
     المختلف
    0.35
    POSITIVE LOGITS
    amorph
    0.51
     wreath
    0.47
     wreaths
    0.47
     garland
    0.46
     illustrious
    0.46
     pronotum
    0.46
     mousse
    0.45
     titleImageUrl
    0.45
    onglet
    0.45
     continuer
    0.43
    Act Density 0.002%

    No Known Activations