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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HeaderView
    -0.06
    FlowLayout
    -0.06
    HttpRequest
    -0.06
    Gay
    -0.06
    SET
    -0.06
    overe
    -0.05
    άβ
    -0.05
    printed
    -0.05
     Bren
    -0.05
    Configuration
    -0.05
    POSITIVE LOGITS
     INITIAL
    0.08
     lethal
    0.07
    ='{
    0.07
    (off
    0.07
     منابع
    0.07
     wilderness
    0.07
    %%
    0.07
    [path
    0.07
    leveland
    0.07
     TableRow
    0.07
    Act Density 0.015%

    No Known Activations