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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ק
    0.51
    Ο
    0.50
    لا
    0.49
    Α
    0.47
    OG
    0.46
    staff
    0.46
    ONI
    0.45
    で
    0.45
    ০০
    0.45
    म
    0.45
    POSITIVE LOGITS
     koje
    0.52
    ことなく
    0.52
     которого
    0.50
     fonctionnalité
    0.48
    anın
    0.48
    <unused2133>
    0.48
     ограничи
    0.47
    <unused374>
    0.47
     které
    0.47
     welke
    0.47
    Act Density 2.090%

    No Known Activations