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

    Neuronpedia

    INDEX
    Explanations

    oracle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -circle
    -0.07
    법
    -0.07
    ’’
    -0.06
    วน
    -0.06
     saw
    -0.06
    300
    -0.06
     chemistry
    -0.06
    embrance
    -0.06
    _direction
    -0.06
     inversion
    -0.06
    POSITIVE LOGITS
     KAR
    0.07
     До
    0.07
     دولت
    0.07
     Engl
    0.07
    apers
    0.07
     newRow
    0.07
     artık
    0.06
     Raptors
    0.06
     Mazda
    0.06
    _ACL
    0.06
    Act Density 0.001%

    No Known Activations