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

    Neuronpedia

    INDEX
    Explanations

    representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .aspx
    -0.07
     INTER
    -0.06
    getTime
    -0.06
                                            ↵
    -0.06
    ráci
    -0.06
     twe
    -0.06
     bullets
    -0.06
    Below
    -0.06
     barrels
    -0.06
    (console
    -0.06
    POSITIVE LOGITS
     الثانية
    0.07
    療
    0.07
    (bc
    0.06
     пару
    0.06
    rolley
    0.06
     Dover
    0.06
    :@"%
    0.06
     UIWindow
    0.06
     pitched
    0.06
    (tm
    0.06
    Act Density 0.005%

    No Known Activations