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

    Neuronpedia

    INDEX
    Explanations

    comprehensive explanation/guide/overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    1.40
     Tất
    1.21
    󰡔
    1.18
    TorpedoStore
    1.13
    라면
    1.13
    푝
    1.13
     işlemler
    1.11
    бина
    1.10
    i
    1.10
    𝙻
    1.09
    POSITIVE LOGITS
    ich
    1.41
    ia
    1.10
    ne
    1.09
    ic
    1.09
    ned
    1.08
    an
    1.06
    на
    1.05
    ts
    1.05
    ile
    1.05
    ta
    1.04
    Act Density 0.113%

    No Known Activations