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

    Neuronpedia

    INDEX
    Explanations

    She saw, was, or tolerated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dispone
    0.46
    奋
    0.45
    <0x00>
    0.43
    鶉
    0.43
     هڪ
    0.43
     performing
    0.43
     stvar
    0.43
     واحدة
    0.42
     plc
    0.42
    φέρον
    0.41
    POSITIVE LOGITS
    reise
    0.45
     turist
    0.44
     turista
    0.44
    وری
    0.42
    チーズ
    0.41
    -
    0.41
    tox
    0.41
    rige
    0.41
     gib
    0.40
    িতেছি
    0.40
    Act Density 0.003%

    No Known Activations