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

    Neuronpedia

    INDEX
    Explanations

    turns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coco
    -0.07
    τει
    -0.06
     mascot
    -0.06
     놀
    -0.06
     subscri
    -0.06
    Total
    -0.06
     hace
    -0.06
     placebo
    -0.06
     partners
    -0.06
     haven
    -0.06
    POSITIVE LOGITS
    umm
    0.06
     liberalism
    0.06
    .","
    0.06
    Broken
    0.06
     Сем
    0.06
     philippines
    0.06
     sexism
    0.06
    ــــــــ
    0.06
    罗
    0.06
    atch
    0.06
    Act Density 0.006%

    No Known Activations