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

    Neuronpedia

    INDEX
    Explanations

    pac followed by man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.41
     (
    1.22
    ों
    1.20
    ní
    1.20
    ners
    1.20
    ओं
    1.18
    nett
    1.15
    ים
    1.10
    ining
    1.03
    pping
    1.02
    POSITIVE LOGITS
    n
    1.34
    *
    1.13
    ্ড
    1.13
    $
    1.12
    ג
    1.12
    ”
    1.07
    l
    1.05
    ");
    1.02
    ل
    1.02
    nThe
    1.02
    Act Density 0.001%

    No Known Activations