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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    We
    0.40
     our
    0.37
    T
    0.36
    L
    0.36
    E
    0.35
    Ů
    0.35
    И
    0.35
    ANG
    0.34
    Т
    0.34
    ALL
    0.34
    POSITIVE LOGITS
     nación
    0.42
     prostit
    0.36
     dragState
    0.35
     Đảng
    0.34
    之类的
    0.33
     xhrObj
    0.33
     whatnot
    0.33
    🫤
    0.33
     ascertaining
    0.33
    🥸
    0.33
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.