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

    Neuronpedia

    INDEX
    Explanations

    response to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marries
    0.77
     खिताब
    0.75
    łada
    0.73
     enviable
    0.73
     marry
    0.72
     championnat
    0.72
     kopen
    0.71
     suing
    0.70
     besuchte
    0.70
     quarrels
    0.70
    POSITIVE LOGITS
     responses
    1.69
     response
    1.57
     respond
    1.42
     responding
    1.41
     responded
    1.40
     Responses
    1.37
    response
    1.31
    responses
    1.31
     Respond
    1.29
     Response
    1.28
    Act Density 4.260%

    No Known Activations