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

    Neuronpedia

    INDEX
    Explanations

    Es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ste
    -0.82
     A
    -0.79
     F
    -0.77
    ,
    -0.76
     
    -0.75
     R
    -0.75
     (
    -0.75
     M
    -0.74
     and
    -0.73
     as
    -0.73
    POSITIVE LOGITS
     myſelf
    1.69
    ſelf
    1.53
     Efq
    1.47
     Jefus
    1.45
     itſelf
    1.45
     Theſe
    1.45
    ſelves
    1.40
     ―――――
    1.37
     ་་
    1.36
     Majefty
    1.35
    Act Density 0.551%

    No Known Activations