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

    Neuronpedia

    INDEX
    Explanations

    common phrases or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    0.49
    Emer
    0.48
    Setting
    0.47
    Date
    0.46
    Bath
    0.46
    Floor
    0.45
    1
    0.44
    Son
    0.43
    スト
    0.42
    Ber
    0.42
    POSITIVE LOGITS
    кансер
    0.48
     경제
    0.48
     निधी
    0.48
    ເກ
    0.47
     수익
    0.46
    ῷ
    0.46
     homomorphisms
    0.46
    কোষ
    0.45
     दोन्ही
    0.45
     ตัว
    0.44
    Act Density 0.037%

    No Known Activations