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

    Neuronpedia

    INDEX
    Explanations

    explain how something is calculated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))`
    0.77
    )–
    0.75
    ยาย
    0.72
    )”
    0.69
    áctica
    0.69
    ),”
    0.69
    )`
    0.68
    ).”
    0.68
    ঞ্
    0.67
     japones
    0.66
    POSITIVE LOGITS
     Tech
    0.73
     LABEL
    0.71
     MSCI
    0.70
     Labels
    0.70
     Schneider
    0.69
     Cras
    0.68
     Culture
    0.68
     Carnival
    0.67
     FOD
    0.64
     MRI
    0.63
    Act Density 0.205%

    No Known Activations