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

    Neuronpedia

    INDEX
    Explanations

    The names of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Specifically
    0.39
    ى
    0.39
    ร่าง
    0.36
    😅
    0.35
    with
    0.35
    最近
    0.35
    只限平日
    0.35
    呈
    0.35
    With
    0.34
     برای
    0.34
    POSITIVE LOGITS
    odore
    0.54
    atrical
    0.52
     plight
    0.44
     odyssey
    0.42
     story
    0.41
    ка
    0.41
     ulcer
    0.39
     beggar
    0.39
    mselves
    0.39
     impact
    0.38
    Act Density 0.122%

    No Known Activations