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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;:
    -0.07
    闭
    -0.06
    echo
    -0.06
    _requirements
    -0.06
    ека
    -0.06
    онов
    -0.06
    straction
    -0.06
    epad
    -0.06
    \base
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     conferences
    0.06
     jun
    0.06
    )}↵
    0.06
     severely
    0.06
     architects
    0.06
    .RES
    0.06
    enter
    0.06
    žený
    0.06
    átky
    0.06
     outpatient
    0.06
    Act Density 0.001%

    No Known Activations