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

    Neuronpedia

    INDEX
    Explanations

    api version numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bred
    -0.08
     :-)
    -0.07
     wür
    -0.07
    _Internal
    -0.06
    Forbidden
    -0.06
    administr
    -0.06
    UIImageView
    -0.06
     Aboriginal
    -0.06
    ]?.
    -0.06
    él
    -0.06
    POSITIVE LOGITS
     상담
    0.08
     ورد
    0.06
     beetle
    0.06
    -byte
    0.06
    -facing
    0.06
     robots
    0.06
     patriotism
    0.06
     Hor
    0.06
     interface
    0.06
    える
    0.06
    Act Density 0.006%

    No Known Activations