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

    Neuronpedia

    INDEX
    Explanations

    Scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     神马收录
    -0.07
    currency
    -0.07
    Cost
    -0.07
    -one
    -0.06
     language
    -0.06
    [N
    -0.06
    _DECL
    -0.06
     cyclic
    -0.06
     Semantic
    -0.06
     Hooks
    -0.06
    POSITIVE LOGITS
     ArrayCollection
    0.06
    ınızda
    0.06
    zburg
    0.06
     propaganda
    0.06
     boto
    0.06
    _goto
    0.06
     subway
    0.06
    ประกอบ
    0.06
    ıp
    0.06
    ambi
    0.06
    Act Density 0.049%

    No Known Activations