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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     flashy
    0.84
     protruding
    0.80
     versatile
    0.70
     superposition
    0.69
     degradation
    0.66
     duo
    0.66
     unconventional
    0.66
     excitation
    0.65
    搭载
    0.65
     irreversible
    0.64
    POSITIVE LOGITS
     membership
    1.42
    membership
    1.38
    Membership
    1.33
     Membership
    1.31
     memberships
    1.23
     члены
    1.23
    會員
    1.21
    Association
    1.18
    会员
    1.16
    association
    1.13
    Act Density 0.687%

    No Known Activations