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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    س
    1.91
    kimi
    1.73
    要有
    1.64
    䩕
    1.64
    }$;
    1.56
    cedented
    1.55
     افراد
    1.55
     의해
    1.55
     예정이다
    1.51
    ндә
    1.49
    POSITIVE LOGITS
    ো
    1.72
    ל
    1.70
     baseman
    1.68
    constant
    1.57
    command
    1.51
     commandment
    1.49
     desalination
    1.49
    u
    1.49
    ap
    1.48
    AS
    1.45
    Act Density 0.308%

    No Known Activations