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

    Neuronpedia

    INDEX
    Explanations

    say ".com"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bru
    -0.07
     doctors
    -0.07
    échange
    -0.07
    (screen
    -0.07
    建立健全
    -0.07
    (det
    -0.07
    _dataset
    -0.06
     diesel
    -0.06
     Jan
    -0.06
    _department
    -0.06
    POSITIVE LOGITS
    ungalow
    0.06
    ,,,
    0.06
    路虎
    0.06
     Rifle
    0.06
     lub
    0.06
     Huffington
    0.06
    ystack
    0.06
    十足
    0.06
     cupboard
    0.06
    万辆
    0.06
    Act Density 0.001%

    No Known Activations