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

    Neuronpedia

    INDEX
    Explanations

    web addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _restart
    -0.08
    instagram
    -0.07
    quota
    -0.07
     intel
    -0.07
    烧烤
    -0.07
     chants
    -0.07
     itm
    -0.07
    בטח
    -0.07
    _photo
    -0.07
     ço
    -0.07
    POSITIVE LOGITS
     Organizer
    0.08
    很有
    0.07
     |--
    0.07
    鱾
    0.07
     resc
    0.07
    _optimizer
    0.07
     apologized
    0.06
     Coupon
    0.06
    よい
    0.06
     organizations
    0.06
    Act Density 0.000%

    No Known Activations