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

    Neuronpedia

    INDEX
    Explanations

    goals and intentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :a
    -0.07
    、
    -0.07
     appreciation
    -0.07
     Encryption
    -0.07
    a
    -0.06
     slaughter
    -0.06
    -weight
    -0.06
    ","
    -0.06
     додатков
    -0.06
     Egyptians
    -0.06
    POSITIVE LOGITS
    _THRESH
    0.07
    (marker
    0.06
    urret
    0.06
    !(:
    0.06
    \Collections
    0.06
     ملی
    0.06
    ASHBOARD
    0.06
    湿
    0.06
    (low
    0.06
     مص
    0.06
    Act Density 0.054%

    No Known Activations