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

    Neuronpedia

    INDEX
    Explanations

    -ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     display
    -0.56
     speak
    -0.53
     catch
    -0.52
    ensively
    -0.52
     rigorously
    -0.51
     show
    -0.50
     estrictamente
    -0.50
     report
    -0.49
     rozm
    -0.49
     discurso
    -0.49
    POSITIVE LOGITS
    featureID
    0.87
    EDEFAULT
    0.75
     оригіналу
    0.72
    Демографія
    0.70
    setof
    0.68
     Савезне
    0.64
     متعلقه
    0.64
    withIdentifier
    0.64
    GOTREF
    0.63
    ArrowToggle
    0.63
    Act Density 0.001%

    No Known Activations