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

    Neuronpedia

    INDEX
    Explanations

    investment, company acquisitions, author Matt Haig

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.57
    ane
    0.55
    то
    0.50
    ayn
    0.50
    s
    0.49
     তুল
    0.46
    ie
    0.46
    ্র
    0.45
     Roundup
    0.44
    ข
    0.44
    POSITIVE LOGITS
    ﻚ
    0.56
     окончания
    0.52
     ⚫
    0.50
     основания
    0.49
    েশ
    0.48
    וס
    0.48
     الرابعه
    0.48
    ků
    0.48
    ଵ
    0.48
    鬏
    0.48
    Act Density 0.001%

    No Known Activations