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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     można
    -0.07
    `;↵
    -0.07
    lation
    -0.07
    .uri
    -0.07
    -lg
    -0.06
    erve
    -0.06
     Terrorism
    -0.06
     nen
    -0.06
    /en
    -0.06
     frustration
    -0.06
    POSITIVE LOGITS
    -original
    0.07
    \brief
    0.07
     Hawai
    0.06
    laden
    0.06
    methodPointerType
    0.06
     rebound
    0.06
    bill
    0.06
    _story
    0.06
     Petite
    0.06
    UniformLocation
    0.06
    Act Density 0.019%

    No Known Activations