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

    Neuronpedia

    INDEX
    Explanations

    Christianity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atti
    -0.07
    (Route
    -0.07
    .AbsoluteConstraints
    -0.07
    .Str
    -0.07
    依照
    -0.07
    另外
    -0.06
     بشكل
    -0.06
    _callbacks
    -0.06
     (++
    -0.06
    それが
    -0.06
    POSITIVE LOGITS
     OST
    0.07
     בתח
    0.07
     Dw
    0.07
     gioc
    0.07
    VectorXd
    0.07
    汹
    0.06
    (inode
    0.06
    重中之
    0.06
    那么简单
    0.06
    веща
    0.06
    Act Density 0.008%

    No Known Activations