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

    Neuronpedia

    INDEX
    Explanations

    document titles and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଣ
    0.85
     線
    0.84
     others
    0.83
    ){}
    0.83
     PAOK
    0.80
     ओडिशा
    0.78
     Kunden
    0.78
    remaining
    0.77
    THERS
    0.77
     वडिला
    0.76
    POSITIVE LOGITS
    [
    0.61
    یاء
    0.59
    Don
    0.59
    Save
    0.57
     [/
    0.56
    ((
    0.56
    Untitled
    0.53
     [
    0.52
    Happy
    0.52
     ((
    0.51
    Act Density 0.098%

    No Known Activations