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

    Neuronpedia

    INDEX
    Explanations

    advocate, asthma, spine, reach, pole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هما
    0.51
    лект
    0.48
    лган
    0.46
    ลำ
    0.45
    䣨
    0.44
    वर्ल्ड
    0.43
    ланд
    0.43
     polyt
    0.43
     alphanumeric
    0.43
    ⑸
    0.43
    POSITIVE LOGITS
    ot
    0.52
    uring
    0.48
    os
    0.48
    ile
    0.47
    </tr>
    0.46
    Im
    0.45
    ue
    0.45
    idi
    0.44
    offre
    0.43
    osp
    0.43
    Act Density 0.009%

    No Known Activations