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

    Neuronpedia

    INDEX
    Explanations

    negativity/taboo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Championships
    -0.07
     Chr
    -0.06
    	reset
    -0.06
    -0.06
    /layout
    -0.06
     довольно
    -0.06
     repeating
    -0.06
    culus
    -0.06
     diferencia
    -0.06
    //================================================
    -0.06
    POSITIVE LOGITS
    55
    0.07
    LAG
    0.06
    �
    0.06
     reinforcements
    0.06
    .rightBarButtonItem
    0.06
    AllArgsConstructor
    0.06
     projev
    0.06
    ourmet
    0.06
     �
    0.06
     reactionary
    0.06
    Act Density 0.103%

    No Known Activations