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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    of
    -0.07
    OF
    -0.07
    C
    -0.07
    ’m
    -0.06
    Μ
    -0.06
    י�
    -0.06
    ’s
    -0.06
    that
    -0.06
    F
    -0.06
    ’
    -0.06
    POSITIVE LOGITS
    گو
    0.08
    	dest
    0.08
    _foreign
    0.08
     rfl
    0.07
    _Cell
    0.07
    _SURFACE
    0.07
    _LONG
    0.07
     trembling
    0.07
    بو
    0.07
    اوت
    0.07
    Act Density 0.425%

    No Known Activations