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

    Neuronpedia

    INDEX
    Explanations

    URLs and medical symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    catenin
    0.97
    methylene
    0.96
    льний
    0.95
    Chair
    0.94
    هایت
    0.94
    Polynomial
    0.90
    gaan
    0.87
    ધા
    0.87
    époque
    0.86
    roasted
    0.86
    POSITIVE LOGITS
     real
    0.80
     like
    0.80
     you
    0.68
     online
    0.66
     blog
    0.66
     온
    0.66
     압
    0.64
     Weird
    0.61
     LIKE
    0.61
     j
    0.61
    Act Density 0.015%

    No Known Activations