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

    Neuronpedia

    INDEX
    Explanations

    concepts and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٤
    0.40
     surgery
    0.39
     adaptability
    0.38
    recover
    0.37
     employability
    0.37
    єте
    0.37
    imwrite
    0.37
     biomedical
    0.36
    రె
    0.36
     agrí
    0.36
    POSITIVE LOGITS
    erex
    0.45
    edin
    0.44
    oler
    0.44
    ayal
    0.44
     crescent
    0.43
    եր
    0.43
     মতোই
    0.42
    εν
    0.42
    ovane
    0.42
    oisin
    0.41
    Act Density 0.014%

    No Known Activations