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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theta
    -0.07
    ीर
    -0.07
    $k
    -0.06
    ينة
    -0.06
     wines
    -0.06
    _le
    -0.06
     Crate
    -0.06
    blr
    -0.06
    Miller
    -0.06
    Girls
    -0.06
    POSITIVE LOGITS
     ');↵
    0.07
     stabbing
    0.06
    訊
    0.06
    SendMessage
    0.06
    Callback
    0.06
    Screens
    0.06
    	LCD
    0.06
    】↵
    0.06
     sci
    0.06
    /trans
    0.06
    Act Density 0.042%

    No Known Activations