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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pl
    -0.07
    ob
    -0.07
     Silence
    -0.07
    edback
    -0.07
    菼
    -0.07
     студент
    -0.07
    פחד
    -0.07
     scor
    -0.07
    дается
    -0.07
     Deal
    -0.07
    POSITIVE LOGITS
     rez
    0.08
    :size
    0.07
    (Arg
    0.07
    保利
    0.07
    urd
    0.07
     inconsist
    0.07
    .isSelected
    0.07
    OLUME
    0.06
    _Mouse
    0.06
    برج
    0.06
    Act Density 0.031%

    No Known Activations