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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ঠা
    0.89
    рый
    0.77
    ların
    0.75
     Mediation
    0.73
    icillin
    0.71
    ρού
    0.71
    ิ
    0.70
    ität
    0.70
    ahir
    0.70
     infliction
    0.70
    POSITIVE LOGITS
    :
    0.75
    Z
    0.73
    elbow
    0.70
    ;
    0.70
    B
    0.66
    え
    0.65
    ও
    0.64
    ः
    0.64
    ಲ್ಲ
    0.63
     ^{
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.