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

    Neuronpedia

    INDEX
    Explanations

    mobile posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faker
    -0.07
     Alexandria
    -0.07
     beide
    -0.07
    Judge
    -0.07
    uncate
    -0.06
     Beacon
    -0.06
     Validator
    -0.06
    _seq
    -0.06
    .Geometry
    -0.06
    悟
    -0.06
    POSITIVE LOGITS
    .DataBind
    0.07
    alıdır
    0.07
     может
    0.07
    __;
    0.06
    ++){
    0.06
    لاین
    0.06
     waving
    0.06
    тесь
    0.06
     pandas
    0.06
     obvious
    0.06
    Act Density 0.014%

    No Known Activations