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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ლა
    0.86
    FAs
    0.84
    bufs
    0.75
    टेन
    0.75
    CONTEXT
    0.72
    azadas
    0.72
    ljed
    0.71
    磯
    0.71
     Акча
    0.70
    츰
    0.70
    POSITIVE LOGITS
     authorizing
    0.76
     relato
    0.75
     timbre
    0.72
     ina
    0.71
     leveling
    0.70
     install
    0.70
     registered
    0.70
     adjustable
    0.69
     thơ
    0.69
     installation
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.