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

    Neuronpedia

    INDEX
    Explanations

    Draw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nikola
    -0.09
    tega
    -0.08
     Mand
    -0.07
    ici
    -0.07
    osta
    -0.07
    ült
    -0.07
     Wend
    -0.07
    izont
    -0.06
    cec
    -0.06
    geist
    -0.06
    POSITIVE LOGITS
     draw
    0.17
     Draw
    0.16
    draw
    0.15
     drawing
    0.12
    Draw
    0.12
     draws
    0.12
    .draw
    0.12
     drawback
    0.11
     Draws
    0.11
     drawn
    0.11
    Act Density 0.016%

    No Known Activations