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

    Neuronpedia

    INDEX
    Explanations

    CPU instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Educación
    -0.09
     guerr
    -0.09
     Montessori
    -0.09
     Hostel
    -0.08
     attraction
    -0.08
     hostel
    -0.08
     reinforcement
    -0.08
     kindergarten
    -0.08
    采访
    -0.08
     lawyer
    -0.08
    POSITIVE LOGITS
     Flags
    0.11
    flags
    0.11
    Flags
    0.11
     flags
    0.10
     prü
    0.09
    	flags
    0.09
     FLAGS
    0.09
    .flags
    0.09
     disables
    0.09
    	results
    0.09
    Act Density 0.002%

    No Known Activations