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

    Neuronpedia

    INDEX
    Explanations

    power generators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pretty
    -0.07
     pretty
    -0.07
    ancy
    -0.07
    QUERY
    -0.06
    validate
    -0.06
    ٍ
    -0.06
    ('{
    -0.06
     walkthrough
    -0.06
    "This
    -0.06
    ourses
    -0.06
    POSITIVE LOGITS
    ')))↵
    0.07
     indifferent
    0.07
     résult
    0.06
    %timeout
    0.06
     quart
    0.06
     LastName
    0.06
    _nt
    0.06
    zeigen
    0.06
     BOOLEAN
    0.06
     polov
    0.06
    Act Density 0.035%

    No Known Activations