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

    Neuronpedia

    INDEX
    Explanations

    search criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jumped
    -0.07
     מ
    -0.07
    該
    -0.06
     doors
    -0.06
     Merkezi
    -0.06
    賢
    -0.06
     blocker
    -0.06
    _EXISTS
    -0.06
    MainThread
    -0.06
     içerisinde
    -0.06
    POSITIVE LOGITS
    =z
    0.07
    408
    0.07
     arom
    0.07
    DialogContent
    0.06
     p
    0.06
    421
    0.06
    ;(
    0.06
     trench
    0.06
    .mongo
    0.06
    》↵
    0.06
    Act Density 0.043%

    No Known Activations