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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ance
    0.42
    bach
    0.41
    messer
    0.41
     제대로
    0.40
    mimpi
    0.40
    Sic
    0.39
    combination
    0.39
     नो
    0.39
    rms
    0.39
    backslash
    0.39
    POSITIVE LOGITS
     семей
    0.52
     striis
    0.47
     Family
    0.47
     když
    0.47
    ívá
    0.46
     quando
    0.45
     när
    0.45
     FAMILY
    0.44
    ធម្ម
    0.44
     détermination
    0.44
    Act Density 0.005%

    No Known Activations