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

    Neuronpedia

    INDEX
    Explanations

    References and numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ankle
    -0.06
     throttle
    -0.06
    orgetown
    -0.06
    licants
    -0.06
     band
    -0.06
    matches
    -0.06
    イント
    -0.06
    serir
    -0.06
    ानद
    -0.06
     fading
    -0.06
    POSITIVE LOGITS
    <context
    0.07
     Powered
    0.07
     rupture
    0.07
     مص
    0.07
     κατά
    0.07
    _at
    0.06
    ?'
    0.06
    TestData
    0.06
     ทาง
    0.06
    国際
    0.06
    Act Density 0.211%

    No Known Activations