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

    Neuronpedia

    INDEX
    Explanations

    legal and factual questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lige
    0.47
    :
    0.47
     herbal
    0.47
    ადი
    0.44
     bland
    0.44
    ани
    0.44
     herb
    0.43
     HSA
    0.43
     sito
    0.43
     gosto
    0.43
    POSITIVE LOGITS
    ructure
    0.46
    rowad
    0.46
    ऊदी
    0.45
    oping
    0.44
    EMPT
    0.44
    unities
    0.42
    ruction
    0.41
     certains
    0.41
    lovakia
    0.41
    organization
    0.41
    Act Density 0.002%

    No Known Activations