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

    Neuronpedia

    INDEX
    Explanations

    closing curly braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IAS
    -0.09
    446
    -0.09
     Daisy
    -0.09
     Ced
    -0.09
    ical
    -0.09
    ãĤ¡
    -0.09
     Rae
    -0.08
     })}\n
    -0.08
     Herrera
    -0.08
     })č\n
    -0.08
    POSITIVE LOGITS
    ï½Ŀ
    0.12
    orna
    0.10
     Kelvin
    0.10
     "}\
    0.09
    ¶Į
    0.09
    aeda
    0.09
    ritel
    0.09
    emmel
    0.09
    ighb
    0.08
    owell
    0.08
    Act Density 0.025%

    No Known Activations