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

    Neuronpedia

    INDEX
    Explanations

    specific phrasing following keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UREMENT
    0.38
    णातील
    0.38
     véh
    0.37
     turnaround
    0.37
    числи
    0.37
    istical
    0.37
    ㎢
    0.36
    Additive
    0.36
     AGAINST
    0.36
    ोला
    0.36
    POSITIVE LOGITS
     Ips
    0.42
    valley
    0.39
    menus
    0.38
     ভদ্র
    0.38
     Peacock
    0.38
    pe
    0.38
    oute
    0.38
     Pain
    0.38
    zina
    0.37
     valley
    0.36
    Act Density 0.001%

    No Known Activations