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

    Neuronpedia

    INDEX
    Explanations

    legal compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    剥离
    -0.07
    ﮣ
    -0.07
    unched
    -0.07
    OTT
    -0.07
     Gale
    -0.07
     YE
    -0.07
    cribing
    -0.07
    ('/')↵
    -0.07
     qualification
    -0.06
    𬶨
    -0.06
    POSITIVE LOGITS
    킨
    0.08
    )((
    0.08
    _af
    0.08
     eighty
    0.07
    슌
    0.07
    彝
    0.07
    _traffic
    0.07
     ironic
    0.07
    רים
    0.07
    렇
    0.07
    Act Density 0.003%

    No Known Activations