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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     siguientes
    -0.07
     χρό
    -0.07
     цих
    -0.07
     Zika
    -0.06
    mit
    -0.06
     TSA
    -0.06
     أو
    -0.06
    142
    -0.06
    정보
    -0.06
     Laden
    -0.06
    POSITIVE LOGITS
     سود
    0.07
    .preference
    0.06
    /non
    0.06
    mnt
    0.06
    (chalk
    0.06
     Aaron
    0.06
    _crop
    0.06
     discrepancies
    0.06
     ${↵
    0.06
    fine
    0.06
    Act Density 0.030%

    No Known Activations