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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الرو
    -0.07
     �
    -0.07
    termin
    -0.07
     mùi
    -0.06
    (idx
    -0.06
     ***!↵
    -0.06
     undergoing
    -0.06
    ู
    -0.06
     نسخ
    -0.06
     ПО
    -0.06
    POSITIVE LOGITS
     nhiệm
    0.07
     ;
↵
    0.06
     ignore
    0.06
    .Search
    0.06
    _IMPORT
    0.06
    ISE
    0.06
    )،
    0.06
    ektor
    0.06
    launch
    0.06
    iedy
    0.06
    Act Density 0.002%

    No Known Activations