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

    Neuronpedia

    INDEX
    Explanations

    gate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :nth
    -0.07
    _resp
    -0.06
     nije
    -0.06
    .ul
    -0.06
     ощ
    -0.06
     thee
    -0.06
     utf
    -0.06
     iets
    -0.06
     Bose
    -0.06
    犯罪
    -0.06
    POSITIVE LOGITS
    tables
    0.07
    ôt
    0.07
    park
    0.07
    sembling
    0.06
    Selector
    0.06
     darn
    0.06
     oven
    0.06
    uj
    0.06
    CONS
    0.06
    spy
    0.06
    Act Density 0.005%

    No Known Activations