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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MUT
    -0.06
    ritical
    -0.06
    225
    -0.06
     Sand
    -0.06
    .RESET
    -0.06
    [last
    -0.06
    '{
    -0.06
    (*)(
    -0.06
    ίο
    -0.06
     erw
    -0.06
    POSITIVE LOGITS
     Accuracy
    0.07
    -par
    0.07
    oids
    0.07
     बर
    0.06
    Inside
    0.06
     fm
    0.06
     advisor
    0.06
     Breast
    0.06
     Dexter
    0.06
     Decorating
    0.06
    Act Density 0.002%

    No Known Activations