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

    Neuronpedia

    INDEX
    Explanations

    Jr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jefus
    -1.05
    expandindo
    -1.05
     Majefty
    -1.05
     Efq
    -1.01
    tvguidetime
    -1.00
    neſs
    -0.99
     myſelf
    -0.98
     ſta
    -0.97
     purpoſe
    -0.93
     Eſ
    -0.92
    POSITIVE LOGITS
    .
    0.68
    .,
    0.63
    ,
    0.62
    ↵↵↵
    0.56
    ...
    0.55
    ;
    0.54
    !
    0.54
    .;
    0.53
     "
    0.52
    ↵
    0.51
    Act Density 0.266%

    No Known Activations