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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cof
    1.02
     Curse
    1.00
     CV
    0.97
     CT
    0.97
     Zombies
    0.93
    ’
    0.93
    病
    0.93
    ق
    0.92
     CD
    0.92
    แค
    0.90
    POSITIVE LOGITS
    desc
    1.07
    そして
    1.03
    Desc
    0.89
    fmt
    0.87
     valamint
    0.86
    GROUP
    0.86
     hå
    0.85
    yj
    0.85
    develop
    0.84
    REQ
    0.84
    Act Density 0.000%

    No Known Activations