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

    Neuronpedia

    INDEX
    Explanations

    questions after prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ای
    0.64
     Lernen
    0.63
    io
    0.57
     Wissenschaft
    0.56
    AN
    0.56
     viento
    0.54
    ine
    0.54
    CHAPTER
    0.53
     und
    0.52
    ROM
    0.51
    POSITIVE LOGITS
    ن
    0.61
    d
    0.60
     arty
    0.60
    ranu
    0.59
     ações
    0.59
    م
    0.58
    摞
    0.58
    座椅
    0.57
    ставки
    0.57
    lás
    0.57
    Act Density 0.000%

    No Known Activations