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

    Neuronpedia

    INDEX
    Explanations

    jsonify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    errs
    -0.08
    etch
    -0.07
     suffers
    -0.07
    Abb
    -0.07
     wiederum
    -0.07
    utico
    -0.07
     coax
    -0.07
     suffered
    -0.07
    Essay
    -0.07
    Chaque
    -0.07
    POSITIVE LOGITS
    ({"
    0.09
     inquiét
    0.08
     {"
    0.08
    ({'
    0.08
     çalışan
    0.08
     motives
    0.08
     confidence
    0.08
     iş
    0.08
     trabajadores
    0.07
    .dumps
    0.07
    Act Density 0.001%

    No Known Activations