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

    Neuronpedia

    INDEX
    Explanations

    free options with limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سپورت
    0.40
    izm
    0.37
    ချ
    0.35
     disturbed
    0.35
     Immutable
    0.34
     Ordered
    0.34
     Imam
    0.33
    히려
    0.33
     أل
    0.33
     Cra
    0.33
    POSITIVE LOGITS
    ABLES
    0.42
     কলে
    0.40
     ಸಲ್ಲ
    0.40
     (,
    0.38
    arro
    0.37
     ({
    0.37
    ADI
    0.36
     („
    0.36
    िसा
    0.36
    ーン
    0.36
    Act Density 0.002%

    No Known Activations