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

    Neuronpedia

    INDEX
    Explanations

    transform

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     artillery
    -0.06
    $$$
    -0.06
    getNext
    -0.06
     lake
    -0.06
    RuntimeException
    -0.06
     fortress
    -0.06
     aster
    -0.06
     parted
    -0.06
    ------------------------------
    -0.06
     ApiException
    -0.06
    POSITIVE LOGITS
    =sum
    0.07
     объем
    0.06
     Sự
    0.06
     度
    0.06
     BIND
    0.06
     регі
    0.06
    摩
    0.06
    Translations
    0.06
    르고
    0.06
    討
    0.06
    Act Density 0.004%

    No Known Activations