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

    Neuronpedia

    INDEX
    Explanations

    nor, lest, even, probably, mainly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     основные
    0.50
    தீ
    0.44
    同时也
    0.43
    িমা
    0.42
    কুল
    0.42
    仑
    0.41
     специальные
    0.41
     TOG
    0.41
    য়ং
    0.40
    案
    0.40
    POSITIVE LOGITS
    '
    0.53
     verfügbar
    0.43
    ;
    0.43
     debated
    0.43
    erweise
    0.43
    ïde
    0.42
     của
    0.41
     debatable
    0.41
     parcialmente
    0.41
    6
    0.41
    Act Density 0.076%

    No Known Activations