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

    Neuronpedia

    INDEX
    Explanations

    guilty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _InitStructure
    -0.07
     Integral
    -0.07
     abbreviation
    -0.07
     misunderstanding
    -0.07
    .Globalization
    -0.07
    建设
    -0.07
     Signing
    -0.06
     efect
    -0.06
     берег
    -0.06
    ims
    -0.06
    POSITIVE LOGITS
    (iterator
    0.07
     WN
    0.06
    ковой
    0.06
    дая
    0.06
     younger
    0.06
    zk
    0.06
    rade
    0.06
    ames
    0.05
     Plum
    0.05
     loyal
    0.05
    Act Density 0.001%

    No Known Activations