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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     foothills
    0.81
    irr
    0.78
    Initialize
    0.77
    ている
    0.75
     moisturizing
    0.74
     moisturizer
    0.74
     limon
    0.74
    Wm
    0.74
    ountains
    0.73
     lotion
    0.73
    POSITIVE LOGITS
     ако
    0.82
     な
    0.77
     Abbreviations
    0.75
     а
    0.73
     нови
    0.73
    ја
    0.72
     бъде
    0.72
    𝗚
    0.72
     بجلی
    0.72
     étudiant
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.