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

    Neuronpedia

    INDEX
    Explanations

    structures and forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unnamed
    -0.08
     Editing
    -0.07
     accurately
    -0.07
     ประเภท
    -0.07
    Sensitive
    -0.07
    ое
    -0.06
    Author
    -0.06
    呼ば
    -0.06
    west
    -0.06
    -=
    -0.06
    POSITIVE LOGITS
    .getSelectionModel
    0.06
     ${↵
    0.06
    ồn
    0.06
    vern
    0.06
    itty
    0.06
    counter
    0.06
     ओवर
    0.06
    ("
    0.06
    "]
↵
    0.06
    孙
    0.06
    Act Density 0.033%

    No Known Activations