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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _plugins
    -0.07
     Yield
    -0.06
     Deng
    -0.06
    ected
    -0.06
     susceptibility
    -0.06
     effected
    -0.06
    ibilit
    -0.06
     Foreign
    -0.06
    Sites
    -0.06
     Angel
    -0.06
    POSITIVE LOGITS
     teas
    0.08
     поє
    0.07
    objc
    0.07
     outra
    0.07
     jasmine
    0.06
    inan
    0.06
    ("#{
    0.06
    <Int
    0.06
    REMOVE
    0.06
    >((
    0.06
    Act Density 0.000%

    No Known Activations