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

    Neuronpedia

    INDEX
    Explanations

    definition and number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாண்ட
    1.10
    "{
    1.05
    }-{
    1.00
     Phylogenetic
    0.99
    пропетров
    0.98
    ্যোগ
    0.96
     "{{
    0.94
     cuello
    0.93
    góc
    0.92
    '{
    0.91
    POSITIVE LOGITS
    l
    1.12
    laws
    1.11
    lau
    1.09
    isar
    1.04
    icz
    1.03
    லா
    1.01
    ốn
    0.96
    ন
    0.94
    äs
    0.93
    ᧐
    0.92
    Act Density 0.001%

    No Known Activations