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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Intr
    -0.08
     плот
    -0.08
     לפת
    -0.08
    .collection
    -0.07
    _object
    -0.07
    一棵
    -0.07
     Bob
    -0.07
     Molly
    -0.07
    棪
    -0.07
    -plan
    -0.07
    POSITIVE LOGITS
     Sticky
    0.07
    .@
    0.07
     substituted
    0.07
    ."<
    0.07
     removable
    0.07
    ❊
    0.07
     return
    0.06
    Summary
    0.06
    REFIX
    0.06
     등을
    0.06
    Act Density 0.000%

    No Known Activations