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

    Neuronpedia

    INDEX
    Explanations

    Hexadecimal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dar
    -0.08
    ична
    -0.07
     ها
    -0.07
    άρχ
    -0.07
    talk
    -0.07
     ♥
    -0.07
    анси
    -0.06
     RI
    -0.06
     headphone
    -0.06
    vik
    -0.06
    POSITIVE LOGITS
     fileName
    0.07
    たちは
    0.07
     podrob
    0.06
    VERRIDE
    0.06
    IPAddress
    0.06
    GraphNode
    0.06
     exporter
    0.06
     sayılı
    0.06
     ModelState
    0.06
    imestamp
    0.06
    Act Density 0.005%

    No Known Activations