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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    993
    -0.07
    .sh
    -0.07
     Kra
    -0.06
     huyết
    -0.06
    Serializer
    -0.06
     archivo
    -0.06
    zilla
    -0.06
     Schwar
    -0.06
    .codec
    -0.06
    /socket
    -0.06
    POSITIVE LOGITS
        ↵
    0.08
         ↵
    0.08
     tehlik
    0.06
    121
    0.06
    acious
    0.06
    Edition
    0.06
    enade
    0.06
    implified
    0.06
        
↵    
↵
    0.06
     volcanic
    0.06
    Act Density 0.019%

    No Known Activations