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

    Neuronpedia

    INDEX
    Explanations

    academic abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Main
    -0.07
    亲切
    -0.07
    ＼
    -0.07
    neath
    -0.07
    仅代表
    -0.07
     Lil
    -0.07
    .XML
    -0.07
    -effect
    -0.07
    angible
    -0.06
     læ
    -0.06
    POSITIVE LOGITS
    _params
    0.06
     ideals
    0.06
    _rsp
    0.06
    (movie
    0.06
    Bob
    0.06
    _graph
    0.06
    체
    0.06
     oggi
    0.06
     sphere
    0.06
    Triple
    0.06
    Act Density 0.014%

    No Known Activations