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

    Neuronpedia

    INDEX
    Explanations

    neural network code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grad
    -0.07
    ober
    -0.07
     réuss
    -0.07
    ตรวจ
    -0.07
     Kinder
    -0.07
    moire
    -0.06
     pol
    -0.06
    阳台
    -0.06
    卫生
    -0.06
    台上
    -0.06
    POSITIVE LOGITS
     =>
    0.08
     (**
    0.07
    (ROOT
    0.07
    _userdata
    0.07
    (me
    0.07
    <Animator
    0.07
    datas
    0.07
     dólares
    0.07
     assumptions
    0.07
    .feed
    0.07
    Act Density 0.005%

    No Known Activations