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

    Neuronpedia

    INDEX
    Explanations

    sentiment, default file handling, specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.08
     âĢ»
    -0.07
    rix
    -0.07
    ...
    -0.07
    ós
    -0.07
     FileInfo
    -0.07
     Legislative
    -0.07
    117
    -0.07
    arded
    -0.07
     \$
    -0.07
    POSITIVE LOGITS
     nonatomic
    0.10
     |--------------------------------------------------------------------------\n
    0.09
    =<?=
    0.08
    <|begin_of_text|>
    0.08
    userManager
    0.08
    rippling
    0.08
    :\/\/
    0.08
    \xf
    0.08
     ilma
    0.08
    ırak
    0.08
    Act Density 0.213%

    No Known Activations