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

    Neuronpedia

    INDEX
    Explanations

    code licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROW
    -0.07
    row
    -0.07
    <Course
    -0.06
     Συν
    -0.06
    ow
    -0.06
     vets
    -0.06
    ACY
    -0.06
     lij
    -0.06
    Office
    -0.06
     às
    -0.06
    POSITIVE LOGITS
     спад
    0.07
     Lightweight
    0.07
    .getMonth
    0.06
    .constants
    0.06
     Gast
    0.06
    .clf
    0.06
    羽
    0.06
    .small
    0.06
     استاند
    0.06
    .word
    0.06
    Act Density 0.003%

    No Known Activations