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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itulo
    -0.07
    quete
    -0.07
     thật
    -0.07
    .Tab
    -0.07
    حاضر
    -0.07
    .curve
    -0.07
    耕地
    -0.07
    副主任
    -0.07
    ацию
    -0.07
     Теперь
    -0.07
    POSITIVE LOGITS
     ostr
    0.08
     [{'
    0.07
     windshield
    0.06
    .fetchone
    0.06
     dose
    0.06
    ]]
    0.06
    ZZ
    0.06
    innerText
    0.06
    ]+\
    0.06
    ]],↵
    0.06
    Act Density 0.004%

    No Known Activations