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

    Neuronpedia

    INDEX
    Explanations

    enthusiastic response after "Hi!"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    특별시
    4.06
    ação
    3.63
    iere
    3.06
    ت
    3.06
    ea
    3.00
    e
    2.95
    aient
    2.94
    een
    2.91
    iendo
    2.89
    ei
    2.89
    POSITIVE LOGITS
    を有
    2.38
    이면
    2.25
    在
    2.19
    은
    2.13
    を探
    2.09
    が多く
    2.02
    на
    1.95
    이야
    1.94
    我也是
    1.93
    を確認
    1.91
    Act Density 0.475%

    No Known Activations