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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Traditions
    0.75
    िल्म
    0.74
     Sélection
    0.73
     paraissent
    0.72
     Sprachen
    0.72
    aszt
    0.72
    ર્સ
    0.71
     Strategies
    0.71
    鯽
    0.71
     Mathematics
    0.71
    POSITIVE LOGITS
    p
    1.01
    muster
    0.88
    m
    0.84
    mrow
    0.79
    partner
    0.79
    t
    0.79
    sighted
    0.76
    AN
    0.75
    hok
    0.75
    phed
    0.74
    Act Density 0.001%

    No Known Activations