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

    Neuronpedia

    INDEX
    Explanations

    safety management text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ster
    0.55
    iams
    0.53
    ics
    0.52
     chut
    0.51
    ra
    0.50
    dog
    0.50
    otu
    0.50
    mars
    0.49
    ?
    0.49
     खरी
    0.49
    POSITIVE LOGITS
    ین
    0.56
    یل
    0.52
     administración
    0.52
     religión
    0.52
    اری
    0.49
    ئی
    0.49
     rendement
    0.48
    ﺒ
    0.47
    이션
    0.46
     بیم
    0.46
    Act Density 0.000%

    No Known Activations