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

    Neuronpedia

    INDEX
    Explanations

    red

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ordo
    -0.60
    yards
    -0.52
    ać
    -0.50
     TAR
    -0.50
    house
    -0.49
     Glo
    -0.48
     Svar
    -0.48
    郎
    -0.46
    TBS
    -0.46
    cels
    -0.46
    POSITIVE LOGITS
    WebServlet
    0.89
    ftagPool
    0.76
     betweenstory
    0.75
     fédé
    0.71
    principalTable
    0.69
    ConstraintMaker
    0.68
    ArrowToggle
    0.65
     démocr
    0.64
     extérieurs
    0.63
     للاسماء
    0.62
    Act Density 0.024%

    No Known Activations