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

    Neuronpedia

    INDEX
    Explanations

    not currently aware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    çĦ
    -0.09
     CN
    -0.09
    idth
    -0.09
    CN
    -0.09
    inson
    -0.09
     Strike
    -0.09
    osit
    -0.09
     ìĤ°
    -0.08
    isis
    -0.08
    ije
    -0.08
    POSITIVE LOGITS
     either
    0.10
     rallying
    0.09
     sink
    0.09
     rally
    0.09
     rallied
    0.09
     struggled
    0.09
     excel
    0.09
    =./
    0.09
    aved
    0.09
    pire
    0.09
    Act Density 0.076%

    No Known Activations