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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mult
    -0.07
    _constraint
    -0.06
    _collection
    -0.06
    Builders
    -0.06
     Nik
    -0.06
    ']."
    -0.06
    ires
    -0.06
     mysteries
    -0.06
     uncovered
    -0.06
    лены
    -0.06
    POSITIVE LOGITS
     کرده
    0.06
     CATEGORY
    0.06
    .extra
    0.06
    .rev
    0.06
     слов
    0.06
     KV
    0.06
    .Submit
    0.06
    */↵
    0.06
     archived
    0.06
    .quiz
    0.06
    Act Density 0.015%

    No Known Activations