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

    Neuronpedia

    INDEX
    Explanations

    closing html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     e
    0.74
    0.74
    -
    0.72
     just
    0.69
     it
    0.68
    ,
    0.68
     on
    0.66
     o
    0.66
     no
    0.66
     to
    0.65
    POSITIVE LOGITS
    Usuario
    1.08
    getSaveLocation
    1.05
    .'</
    1.05
    Newline
    1.05
    垀
    1.04
    <unused1654>
    1.03
    ávat
    1.02
     tcpHeader
    1.02
    꾿
    1.00
    ;</
    1.00
    Act Density 0.538%

    No Known Activations