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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SELECT
    -0.07
    adients
    -0.07
     TValue
    -0.07
     cavalry
    -0.06
     infiltr
    -0.06
    "));
↵
↵
    -0.06
     Sit
    -0.06
     HID
    -0.06
    Column
    -0.06
    );
↵
↵
    -0.06
    POSITIVE LOGITS
     انگلیسی
    0.07
     Preis
    0.06
     Grocery
    0.06
     california
    0.06
    (WIN
    0.06
     Carpenter
    0.06
    세대
    0.06
    iece
    0.06
    due
    0.06
     석
    0.06
    Act Density 0.010%

    No Known Activations