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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IOC
    -0.06
    LinearLayout
    -0.06
    ackages
    -0.06
    PropertyValue
    -0.06
     honey
    -0.06
     dramatic
    -0.06
     outcomes
    -0.06
     robotic
    -0.06
     citation
    -0.06
     knockout
    -0.06
    POSITIVE LOGITS
    ॰
    0.07
    ss
    0.07
    韓
    0.07
    itta
    0.07
    stoi
    0.07
     examined
    0.06
     beta
    0.06
     vk
    0.06
    ุนายน
    0.06
     آقای
    0.06
    Act Density 0.020%

    No Known Activations