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

    Neuronpedia

    INDEX
    Explanations

    spectrum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phase
    -0.08
     Levine
    -0.07
     phase
    -0.07
     quadratic
    -0.07
     reasonable
    -0.07
    day
    -0.07
    Day
    -0.07
     Job
    -0.07
    Friends
    -0.07
     Joan
    -0.07
    POSITIVE LOGITS
     Spectrum
    0.07
     절
    0.07
     spectral
    0.07
     гум
    0.07
    .setCellValue
    0.07
    谱
    0.07
     استرات
    0.06
    .metroLabel
    0.06
    裁
    0.06
    услов
    0.06
    Act Density 0.011%

    No Known Activations