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

    Neuronpedia

    INDEX
    Explanations

    json code parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ={[
    0.69
    ([
    0.57
    (((
    0.54
    Five
    0.52
    ((-
    0.51
    Housing
    0.51
    ({
    0.50
    ={
    0.49
    [
    0.49
    Heaven
    0.49
    POSITIVE LOGITS
     "__
    0.72
     nameof
    0.71
     '__
    0.69
     "_
    0.60
    nameof
    0.58
     '_
    0.56
     JsonResult
    0.55
     toJson
    0.54
     noreferrer
    0.53
    entario
    0.52
    Act Density 0.175%

    No Known Activations