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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erun
    0.33
     দুর্দান্ত
    0.31
     axiomatic
    0.30
    topo
    0.30
    soever
    0.29
    utant
    0.29
    manip
    0.29
     começar
    0.29
     nomenclature
    0.28
     exoskeleton
    0.28
    POSITIVE LOGITS
    4
    0.44
    7
    0.41
    5
    0.40
    3
    0.40
    2
    0.38
     グリーン
    0.36
     ピンク
    0.36
     dijo
    0.35
     empresas
    0.35
     лечения
    0.34
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.