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

    Neuronpedia

    INDEX
    Explanations

    try

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acie
    -0.07
     toddler
    -0.07
     aer
    -0.07
    imb
    -0.07
    有点
    -0.07
    Their
    -0.07
     negate
    -0.06
    _ic
    -0.06
     McConnell
    -0.06
     getInfo
    -0.06
    POSITIVE LOGITS
    ኃ
    0.09
    quierda
    0.07
    췬
    0.07
    ǫ
    0.07
     대
    0.07
    .TestCase
    0.07
    �
    0.07
    一线城市
    0.07
    质量安全
    0.07
    .responseText
    0.07
    Act Density 0.000%

    No Known Activations