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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rinsim
    0.57
     कल्चर
    0.55
    🔋
    0.54
     กำ
    0.52
    ทัน
    0.52
     காற்ற
    0.51
    пря
    0.50
    kaŭ
    0.50
    мию
    0.50
     लैंग्वे
    0.50
    POSITIVE LOGITS
    \
    0.54
    :
    0.49
    wartz
    0.48
     D
    0.44
    6
    0.44
     Adler
    0.44
    ro
    0.43
     J
    0.42
     prensa
    0.42
    <0xE3>
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.