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

    Neuronpedia

    INDEX
    Explanations

    structured lists and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    еты
    0.50
    Conse
    0.50
    druk
    0.47
    moder
    0.46
    Kong
    0.46
    g
    0.45
    alada
    0.45
    ā
    0.45
    ны
    0.45
    า
    0.45
    POSITIVE LOGITS
     tumors
    0.51
     surgical
    0.49
     weighted
    0.49
     plotted
    0.47
     angiogenic
    0.47
     for
    0.46
     smear
    0.46
     sculpted
    0.46
     চিন্তা
    0.46
     biliary
    0.45
    Act Density 0.001%

    No Known Activations