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

    Neuronpedia

    INDEX
    Explanations

    300, 400

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Foo
    -0.06
     кур
    -0.06
     Abr
    -0.06
     Sin
    -0.06
    Trou
    -0.06
    Culture
    -0.06
     зрост
    -0.06
    pci
    -0.06
    .fp
    -0.06
     spéc
    -0.06
    POSITIVE LOGITS
     polarization
    0.07
     muscles
    0.06
     Loved
    0.06
     QMessageBox
    0.06
    OTOS
    0.06
     atoms
    0.06
    经
    0.06
    itations
    0.06
     pull
    0.06
    σματα
    0.06
    Act Density 0.002%

    No Known Activations