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

    Neuronpedia

    INDEX
    Explanations

    siblings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iminal
    -0.08
    ασίας
    -0.07
     reputable
    -0.07
    ランス
    -0.07
    tim
    -0.07
    itemId
    -0.06
    .Italic
    -0.06
    Wei
    -0.06
     duplex
    -0.06
    “And
    -0.06
    POSITIVE LOGITS
     Curl
    0.07
    TestCategory
    0.07
    (attributes
    0.07
    			↵			↵
    0.06
     потрап
    0.06
    (head
    0.06
     П
    0.06
    opor
    0.06
     úkol
    0.06
     ERR
    0.06
    Act Density 0.005%

    No Known Activations