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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ise
    -0.07
    ic
    -0.07
    抗菌
    -0.07
    -known
    -0.07
    ico
    -0.07
    ⼯
    -0.07
    ali
    -0.07
    actions
    -0.07
    Pooling
    -0.07
    icus
    -0.07
    POSITIVE LOGITS
    Выб
    0.08
    くだ
    0.07
    vrier
    0.07
     jeder
    0.07
     keyValue
    0.07
     jed
    0.07
     vibes
    0.06
    Flexible
    0.06
     søker
    0.06
     פרשת
    0.06
    Act Density 0.004%

    No Known Activations