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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    u
    2.40
    क्षिप्त
    2.30
    𝑒
    2.04
    y
    2.02
    naj
    1.90
    m
    1.90
    에
    1.88
    oise
    1.86
    dru
    1.81
    r
    1.78
    POSITIVE LOGITS
    ╼
    2.35
    થા
    2.27
     jî
    2.27
    ifício
    2.20
    íes
    2.16
    ídio
    2.15
    থায়
    2.15
    orithms
    2.10
    νον
    2.10
    里斯
    2.09
    Act Density 0.283%

    No Known Activations