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

    Neuronpedia

    INDEX
    Explanations

    Technical issues and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حضور
    -0.07
     cục
    -0.07
     MANY
    -0.07
     Jiří
    -0.06
     душ
    -0.06
    ，不过
    -0.06
     Anne
    -0.06
    (xpath
    -0.06
     країни
    -0.06
     Daddy
    -0.06
    POSITIVE LOGITS
    Areas
    0.07
    이
    0.06
    ffffffff
    0.06
    !;↵
    0.06
     insider
    0.06
    (environment
    0.06
    >({
    0.06
     minutes
    0.06
    maktadır
    0.06
    Reduce
    0.06
    Act Density 0.000%

    No Known Activations