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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    校
    -0.07
    🚂
    -0.07
    轉
    -0.07
    噘
    -0.06
    晢
    -0.06
    ᵭ
    -0.06
    岬
    -0.06
    שמים
    -0.06
     לוקח
    -0.06
    バイク
    -0.06
    POSITIVE LOGITS
     stratég
    0.07
    .Sin
    0.07
     routing
    0.07
    .standard
    0.06
    URING
    0.06
    CAD
    0.06
    .location
    0.06
    MF
    0.06
     Structural
    0.06
     Psychology
    0.06
    Act Density 0.002%

    No Known Activations