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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伭
    -0.07
    os
    -0.07
    alom
    -0.07
    annes
    -0.06
    栖
    -0.06
    贞
    -0.06
    寂
    -0.06
     Tee
    -0.06
    bounded
    -0.06
    _algo
    -0.06
    POSITIVE LOGITS
    Canada
    0.08
    .EventQueue
    0.07
    ℞
    0.07
    月
    0.07
    Between
    0.07
    /
↵
    0.07
     comparison
    0.07
    起
    0.06
    'email
    0.06
     międz
    0.06
    Act Density 0.002%

    No Known Activations