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

    Neuronpedia

    INDEX
    Explanations

    Lack of choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Column
    -0.07
     remorse
    -0.07
     Digit
    -0.07
     φ
    -0.06
    _Row
    -0.06
     Ur
    -0.06
    47
    -0.06
    .Web
    -0.06
     рев
    -0.06
     Beg
    -0.06
    POSITIVE LOGITS
    aley
    0.06
    /gallery
    0.06
    /errors
    0.06
    -west
    0.06
    /apple
    0.06
    paramref
    0.06
    现代
    0.06
     organised
    0.06
    @example
    0.06
     router
    0.06
    Act Density 0.079%

    No Known Activations