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

    Neuronpedia

    INDEX
    Explanations

    commas and curly braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -notification
    -0.06
    .Authorization
    -0.06
    716
    -0.06
    (first
    -0.06
    ้บร
    -0.06
     lev
    -0.06
    -results
    -0.06
    'L
    -0.06
     LIABILITY
    -0.06
     machinery
    -0.06
    POSITIVE LOGITS
     Sé
    0.07
    دانلود
    0.07
    _margin
    0.07
     withRouter
    0.06
     člověk
    0.06
    aque
    0.06
    Depending
    0.06
     %>
    0.06
     详情
    0.06
    niž
    0.06
    Act Density 0.016%

    No Known Activations