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

    Neuronpedia

    INDEX
    Explanations

    after an option or comment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.57
    י
    1.45
    navigationItem
    1.44
    i
    1.43
    ੀ
    1.43
    ি
    1.40
    a
    1.38
    ી
    1.36
    ০
    1.35
    ل
    1.34
    POSITIVE LOGITS
     anc
    1.40
     destinada
    1.38
     pretende
    1.33
     लक्षण
    1.29
    $-
    1.25
     debe
    1.15
    ُر
    1.14
     tantas
    1.13
     اینکه
    1.13
     tins
    1.12
    Act Density 0.001%

    No Known Activations