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

    Neuronpedia

    INDEX
    Explanations

    specific named entities and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🫶
    1.19
    🥹
    1.14
    🤍
    1.11
    🤎
    1.11
    🥲
    1.09
    🩷
    1.09
    🫂
    1.05
    🫠
    1.03
    🥸
    1.03
    🫣
    0.98
    POSITIVE LOGITS
     ২০১৭
    1.33
    Brexit
    1.13
     Brexit
    1.11
     ২০১৬
    1.03
     ২০১৮
    1.01
    Trump
    0.94
     Trump
    0.86
    🖒
    0.80
     Zika
    0.77
     selfie
    0.70
    Act Density 0.111%

    No Known Activations