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

    Neuronpedia

    INDEX
    Explanations

    research paper abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corrected
    -0.07
     roadside
    -0.06
     Rabbi
    -0.06
     Republican
    -0.06
    Labels
    -0.06
     *.
    -0.06
    croll
    -0.06
    docs
    -0.06
     Anyone
    -0.06
    Это
    -0.06
    POSITIVE LOGITS
     delve
    0.06
    oven
    0.06
     дів
    0.06
    漂
    0.06
     porad
    0.06
    保
    0.06
    iế
    0.06
    _ADV
    0.06
    .closePath
    0.06
     Strait
    0.06
    Act Density 0.074%

    No Known Activations