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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     potrivit
    0.42
     planilla
    0.40
    неопр
    0.39
     plaie
    0.39
     защото
    0.38
    テープ
    0.38
     முதல்வர்
    0.37
     града
    0.37
     poiché
    0.37
    👅
    0.37
    POSITIVE LOGITS
    High
    0.38
     High
    0.38
     comfortably
    0.37
     inherently
    0.37
     Hing
    0.36
    cy
    0.36
    Ke
    0.36
     passionate
    0.35
     Musik
    0.35
    Tom
    0.35
    Act Density 0.000%

    No Known Activations