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

    Neuronpedia

    INDEX
    Explanations

    all directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +-+-+-+-
    -0.07
    _accum
    -0.07
    对标
    -0.07
    写字楼
    -0.06
     katkı
    -0.06
    찡
    -0.06
    这个地图
    -0.06
    .second
    -0.06
    importDefault
    -0.06
    颡
    -0.06
    POSITIVE LOGITS
     ת
    0.07
     Joi
    0.07
     mandate
    0.07
     outreach
    0.07
     param
    0.07
     *))
    0.07
     shuffle
    0.07
    phinx
    0.07
    phabet
    0.07
    دفع
    0.07
    Act Density 0.002%

    No Known Activations