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

    Neuronpedia

    INDEX
    Explanations

    review requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scoped
    -0.07
     plainly
    -0.07
     Sovere
    -0.06
    ของร
    -0.06
    Ak
    -0.06
    odzi
    -0.06
    tarı
    -0.06
    )$
    -0.06
     parses
    -0.06
    _months
    -0.06
    POSITIVE LOGITS
    reau
    0.08
    nung
    0.07
    软件
    0.07
     conqu
    0.06
    (hw
    0.06
     задов
    0.06
    な
    0.06
    -readable
    0.06
     Commercial
    0.06
    ARATION
    0.06
    Act Density 0.047%

    No Known Activations