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

    Neuronpedia

    INDEX
    Explanations

    wishes for success and regards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tweets
    0.68
    CORPOR
    0.68
    TITLE
    0.67
    warna
    0.67
    MUSIC
    0.66
     TYPE
    0.65
     worsen
    0.64
    SPEAK
    0.64
    ↵
    0.64
    selves
    0.64
    POSITIVE LOGITS
    с
    0.97
    ра
    0.86
    в
    0.84
    부터
    0.80
    ку
    0.79
     electrón
    0.75
    дить
    0.74
    (\
    0.72
    ibly
    0.72
    ма
    0.71
    Act Density 0.001%

    No Known Activations