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

    Neuronpedia

    INDEX
    Explanations

    reports/conclusions/processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Closing
    -0.76
    kepada
    -0.73
    rably
    -0.72
     étoit
    -0.70
    Completed
    -0.70
    Closing
    -0.70
    antaranya
    -0.70
     closing
    -0.69
     cuadros
    -0.69
     Completed
    -0.66
    POSITIVE LOGITS
    XmlAccessType
    0.62
    تقاوى
    0.57
    Erstellt
    0.51
    IARC
    0.51
    WindowConstants
    0.50
    protoc
    0.49
     مرت
    0.47
    Biographie
    0.47
     erf
    0.46
     Riv
    0.46
    Act Density 0.331%

    No Known Activations