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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Categories
    -0.07
    argument
    -0.06
    _sparse
    -0.06
    .Or
    -0.06
    _ports
    -0.06
    _preference
    -0.06
    ве
    -0.06
    -qu
    -0.06
    FPS
    -0.06
    unde
    -0.06
    POSITIVE LOGITS
     ['$
    0.07
    (mContext
    0.07
     restoring
    0.07
    (outputs
    0.07
     paar
    0.06
     prevail
    0.06
     CGRectGet
    0.06
     Kohana
    0.06
    .ascii
    0.06
     yar
    0.06
    Act Density 0.003%

    No Known Activations