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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     preval
    1.08
     че
    1.01
    धारण
    1.00
     fairness
    0.99
     forfe
    0.97
    am
    0.97
     Ehren
    0.95
     ఘ
    0.95
     originated
    0.95
     abundances
    0.95
    POSITIVE LOGITS
    т
    1.24
    ্লে
    1.22
    stup
    1.14
     compuestos
    1.12
    firefox
    1.12
    yap
    1.11
    િ
    1.11
    िक
    1.10
    Ź
    1.10
    melon
    1.09
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.