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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ttl
    2.03
    rlig
    1.97
    蒾
    1.93
    ggen
    1.93
    ttes
    1.89
    פט
    1.88
    DebugType
    1.87
    лле
    1.87
    COMMIT
    1.85
    اا
    1.85
    POSITIVE LOGITS
    REETYPE
    2.16
    ுகள்
    2.05
    ulkner
    1.90
    دع
    1.79
    ுகளை
    1.78
    گیز
    1.78
     Throwable
    1.78
    ுக
    1.76
    간
    1.75
    egg
    1.75
    Act Density 0.052%

    No Known Activations