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

    Neuronpedia

    INDEX
    Explanations

    poetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (vc
    -0.06
    .Http
    -0.06
    ume
    -0.06
    .д
    -0.06
     `,↵
    -0.06
    '){
    -0.06
     khỏi
    -0.06
    .Start
    -0.06
    strpos
    -0.06
    _int
    -0.06
    POSITIVE LOGITS
     Legislature
    0.07
     WI
    0.07
    нах
    0.07
    аті
    0.07
     Stroke
    0.06
     quả
    0.06
     Вар
    0.06
    strup
    0.06
    gather
    0.06
    획
    0.06
    Act Density 0.075%

    No Known Activations