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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     easy
    0.60
     good
    0.59
     excellent
    0.59
     j
    0.55
     superb
    0.55
     beautiful
    0.54
     brightness
    0.54
     hardness
    0.54
     sturdy
    0.52
     impeccable
    0.52
    POSITIVE LOGITS
    原則
    0.52
    蜒
    0.52
    分别
    0.51
    を参照
    0.51
    祀
    0.50
    गुर
    0.50
    {\$
    0.47
     específ
    0.47
     participación
    0.47
     అర
    0.46
    Act Density 0.016%

    No Known Activations