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

    Neuronpedia

    INDEX
    Explanations

    like this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ti
    0.49
    ni
    0.45
    tains
    0.44
    tidak
    0.42
    اں
    0.41
    ting
    0.41
    cart
    0.40
    ton
    0.39
    冫
    0.39
    ten
    0.39
    POSITIVE LOGITS
    螂
    0.43
    ្នែក
    0.43
    <bos>
    0.41
    ö
    0.40
    こんな
    0.40
    습
    0.40
     spiller
    0.40
    ுள்ளார்
    0.40
    pected
    0.40
     تحد
    0.40
    Act Density 0.050%

    No Known Activations