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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    d
    0.17
    f
    0.16
    ↵
    0.16
    5
    0.16
    1
    0.15
    and
    0.15
    t
    0.15
    i
    0.15
    x
    0.15
    it
    0.15
    POSITIVE LOGITS
     wikipagina
    0.15
     dentées
    0.15
    点了点头
    0.14
     striées
    0.14
     postérieur
    0.14
    Missense
    0.14
     függvény
    0.14
     miesią
    0.13
    鳃
    0.13
    🦦
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.