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

    Neuronpedia

    INDEX
    Explanations

    locations, brands, and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.81
    то
    0.75
    ש
    0.73
    ا
    0.71
    ت
    0.71
    ત
    0.70
    기
    0.70
    자
    0.70
    ת
    0.70
    т
    0.69
    POSITIVE LOGITS
    ↵
    0.82
     Technology
    0.60
    ight
    0.56
    otion
    0.51
     Biotechnology
    0.51
    -
    0.51
    alk
    0.50
    :
    0.50
     biotechnology
    0.50
    ati
    0.49
    Act Density 0.050%

    No Known Activations