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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Illum
    -0.07
     fright
    -0.06
     Squadron
    -0.06
     decoder
    -0.06
     motions
    -0.06
    .Diff
    -0.06
    $tpl
    -0.06
     SETTINGS
    -0.06
     Rut
    -0.06
    Ax
    -0.06
    POSITIVE LOGITS
    places
    0.07
    azines
    0.06
     republika
    0.06
     naturally
    0.06
     connection
    0.06
     dwell
    0.06
     realise
    0.06
    DONE
    0.06
    */↵↵
    0.06
    だと
    0.06
    Act Density 0.066%

    No Known Activations