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

    Neuronpedia

    INDEX
    Explanations

    book editions/translations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Descriptions
    -0.06
    <Test
    -0.06
     webs
    -0.06
     manage
    -0.06
     Я
    -0.06
    .respond
    -0.06
    _dst
    -0.06
    %D
    -0.06
    _dependency
    -0.06
    期待
    -0.05
    POSITIVE LOGITS
    Arizona
    0.07
    .isRequired
    0.07
    оу
    0.07
     речов
    0.07
     récup
    0.07
     containerView
    0.06
     Ağustos
    0.06
    killer
    0.06
     относ
    0.06
     primeira
    0.06
    Act Density 0.014%

    No Known Activations