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

    Neuronpedia

    INDEX
    Explanations

    can access information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чём
    0.56
     फ़रवरी
    0.49
    0.49
     Krankheit
    0.47
    储备
    0.47
    ственная
    0.47
    矗
    0.47
     szeptember
    0.46
    ការពារ
    0.46
    根
    0.46
    POSITIVE LOGITS
     فی
    0.48
    o
    0.47
     automation
    0.46
    in
    0.46
     leisurely
    0.46
     त्या
    0.45
     robotic
    0.44
    API
    0.43
     refinance
    0.42
     Turk
    0.41
    Act Density 0.000%

    No Known Activations