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

    Neuronpedia

    INDEX
    Explanations

    choices and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wh
    -0.07
     encompasses
    -0.07
    628
    -0.07
    rep
    -0.06
     Le
    -0.06
    Kal
    -0.06
    شه
    -0.06
    Le
    -0.06
     resemblance
    -0.06
     části
    -0.06
    POSITIVE LOGITS
    ydro
    0.07
    (木
    0.07
     isnt
    0.07
     Welch
    0.06
    植物
    0.06
    ilee
    0.06
    .weapon
    0.06
     waren
    0.06
    aders
    0.06
    ugo
    0.06
    Act Density 0.089%

    No Known Activations