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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.80
    ，
    0.77
    ،
    0.75
     a
    0.72
     ،
    0.66
    0.62
    #
    0.57
    ,
    0.57
     this
    0.54
     allere
    0.52
    POSITIVE LOGITS
    ون
    0.92
    ის
    0.77
    and
    0.75
    на
    0.75
    ل
    0.73
    ق
    0.72
    ные
    0.71
    kan
    0.71
    ری
    0.66
    ور
    0.66
    Act Density 7.189%

    No Known Activations