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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dones
    0.55
     Icons
    0.55
     Preferences
    0.54
     ALLOW
    0.52
     for
    0.51
     GUT
    0.50
     GLUT
    0.50
     UNE
    0.49
     r
    0.49
    ั
    0.49
    POSITIVE LOGITS
    ropolitan
    0.58
    ຢູ່ໃນ
    0.56
    ículo
    0.55
    amia
    0.55
    ț
    0.54
    erio
    0.52
    adiq
    0.52
    ceptible
    0.52
    adel
    0.51
    landish
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.