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

    Neuronpedia

    INDEX
    Explanations

    uncertainty and negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    斯
    -0.08
     детей
    -0.07
    _has
    -0.07
    Grand
    -0.06
    Fair
    -0.06
    "When
    -0.06
    sumer
    -0.06
    _CANNOT
    -0.06
     Carl
    -0.06
    шли
    -0.06
    POSITIVE LOGITS
     BL
    0.07
     �
    0.07
     ()↵↵
    0.07
    ***↵
    0.07
    ///↵
    0.07
     تخ
    0.06
     inund
    0.06
     dissoci
    0.06
     jasmine
    0.06
    ’↵↵
    0.06
    Act Density 0.039%

    No Known Activations