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

    Neuronpedia

    INDEX
    Explanations

    router

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.77
    ########.
    -0.77
    AddTagHelper
    -0.77
    ValueStyle
    -0.71
    __*/
    -0.70
     baby
    -0.70
    AddHtmlAttribute
    -0.69
    +#+#
    -0.68
     GenerationType
    -0.65
     boy
    -0.64
    POSITIVE LOGITS
    ed
    0.57
    ist
    0.55
    ie
    0.54
    owner
    0.54
    y
    0.53
    dit
    0.53
    me
    0.52
    do
    0.52
    set
    0.51
    ia
    0.51
    Act Density 1.615%

    No Known Activations