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

    Neuronpedia

    INDEX
    Explanations

    easy to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙀
    1.11
    𝙖
    1.08
    हरु
    1.07
    𝙊
    1.07
    𝙩
    1.07
    at
    1.03
    𝙙
    1.02
    पद
    1.02
     giấc
    1.01
    𝙮
    1.00
    POSITIVE LOGITS
    н
    0.82
    реза
    0.82
     хуже
    0.81
     breezy
    0.81
    페이지
    0.81
     Tina
    0.78
    餸
    0.78
    עת
    0.78
    ул
    0.77
    ре
    0.76
    Act Density 0.035%

    No Known Activations