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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     towers
    0.38
     doses
    0.37
    λώ
    0.37
     NoContent
    0.37
     आईं
    0.36
     jp
    0.36
     Towers
    0.35
     McKay
    0.35
     lp
    0.35
    érez
    0.35
    POSITIVE LOGITS
    紫
    0.43
    盉
    0.41
     Purple
    0.41
    purple
    0.37
     absorbance
    0.36
     purple
    0.36
    Purple
    0.36
    隀
    0.35
     Phnom
    0.35
     potencia
    0.35
    Act Density 0.007%

    No Known Activations