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

    Neuronpedia

    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     requests
    -0.07
    _TD
    -0.07
    fname
    -0.07
     senators
    -0.06
     Backup
    -0.06
    stim
    -0.06
    klä
    -0.06
    _plan
    -0.06
     bn
    -0.06
    Cy
    -0.06
    POSITIVE LOGITS
     enormously
    0.07
     hữu
    0.07
    ีนาคม
    0.06
     confidently
    0.06
     державного
    0.06
     Constitution
    0.06
    ใหม
    0.06
    =>
    0.06
    _IDX
    0.06
    <L
    0.06
    Act Density 0.022%

    No Known Activations