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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     השני
    -0.08
     مثل
    -0.07
     dernière
    -0.07
     muestra
    -0.07
     tây
    -0.07
    ✦
    -0.07
    Pointer
    -0.07
     Stranger
    -0.07
    .si
    -0.07
     fn
    -0.07
    POSITIVE LOGITS
    cakes
    0.06
    quoted
    0.06
    ４
    0.06
    trad
    0.06
    Cas
    0.06
    dater
    0.06
     商品
    0.06
     Capcom
    0.06
    蚶
    0.06
    缴纳
    0.06
    Act Density 0.011%

    No Known Activations