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

    Neuronpedia

    INDEX
    Explanations

    methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    描
    -0.06
     نيز
    -0.06
    ONLY
    -0.06
    中学
    -0.06
    <Boolean
    -0.06
    خانه
    -0.06
     bureaucrats
    -0.06
     resid
    -0.06
    doing
    -0.06
    то
    -0.05
    POSITIVE LOGITS
    -energy
    0.07
    .paging
    0.06
     getUserId
    0.06
     talents
    0.06
    ків
    0.06
     kick
    0.06
    .languages
    0.06
    -face
    0.06
     ค
    0.06
    .calculate
    0.06
    Act Density 0.005%

    No Known Activations