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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mu
    -0.07
     Jared
    -0.07
    .error
    -0.06
    Versions
    -0.06
    ricing
    -0.06
     foreclosure
    -0.06
     manip
    -0.06
     Associated
    -0.06
    リン
    -0.06
    queue
    -0.06
    POSITIVE LOGITS
     Marines
    0.06
    BASEPATH
    0.06
     Spoon
    0.06
     Countries
    0.06
     revoked
    0.06
    庫
    0.06
    /material
    0.06
    .init
    0.06
     الشركة
    0.06
    851
    0.06
    Act Density 0.351%

    No Known Activations