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

    Neuronpedia

    INDEX
    Explanations

    reshape, measures, graph, utilize, cover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     residents
    0.41
     convince
    0.41
    parentElement
    0.39
    Geme
    0.37
     tế
    0.37
     boomers
    0.37
     PRESSURE
    0.36
    фро
    0.36
    তুল
    0.36
     inwoners
    0.36
    POSITIVE LOGITS
     avulla
    0.41
    ⌯
    0.41
    㥉
    0.41
    Ding
    0.40
     哦
    0.40
    伨
    0.39
     ayudará
    0.39
    ້ນ
    0.38
    瘘
    0.38
    組み合わせ
    0.38
    Act Density 0.000%

    No Known Activations