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

    Neuronpedia

    INDEX
    Explanations

    html DOCTYPE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    3.00
    ный
    2.26
    comboBox
    2.12
    ם
    2.07
     salient
    1.99
     dozen
    1.97
     handful
    1.94
     ∂
    1.94
     sive
    1.93
    doors
    1.92
    POSITIVE LOGITS
    ла
    2.62
    म
    2.57
    ل
    2.55
    ০
    2.41
    DOCTYPE
    2.31
    ис
    2.10
    ം
    2.09
    ্ত
    2.06
    u
    2.04
    ம்
    2.02
    Act Density 0.002%

    No Known Activations