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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incentive
    -0.07
     inputs
    -0.07
     dll
    -0.06
     innate
    -0.06
     enviado
    -0.06
    irm
    -0.06
     ration
    -0.06
     replaces
    -0.06
    ß
    -0.06
     crawling
    -0.06
    POSITIVE LOGITS
     buffalo
    0.06
     sito
    0.06
    know
    0.06
    ازد
    0.06
    .HashMap
    0.06
    '](
    0.06
    ))↵↵
    0.06
    |(↵
    0.06
     우
    0.06
    _TEAM
    0.06
    Act Density 0.002%

    No Known Activations