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

    Neuronpedia

    INDEX
    Explanations

    code/errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lack
    -0.07
    rray
    -0.07
    Africa
    -0.07
    '}↵↵
    -0.07
    clarsimp
    -0.07
    涵盖了
    -0.07
    """
↵
↵
    -0.07
     nutshell
    -0.07
    swith
    -0.07
    袭击
    -0.07
    POSITIVE LOGITS
     rent
    0.07
    츰
    0.07
    .Text
    0.07
    click
    0.07
     запис
    0.06
    عر
    0.06
     meno
    0.06
    score
    0.06
    💝
    0.06
    ро
    0.06
    Act Density 0.037%

    No Known Activations