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

    Neuronpedia

    INDEX
    Explanations

    He

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵
    -1.23
     (
    -1.23
    ,
    -1.15
    ↵↵
    -1.13
    .
    -1.06
     "
    -1.03
     
    -1.03
     -
    -0.99
     or
    -0.96
    /
    -0.95
    POSITIVE LOGITS
     myſelf
    2.13
     ―――――
    1.92
     Efq
    1.92
     itſelf
    1.91
     Monfieur
    1.91
     Anſ
    1.87
     iſt
    1.86
     $_"
    1.86
    ^(@)
    1.84
     himſelf
    1.84
    Act Density 0.392%

    No Known Activations