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

    Neuronpedia

    INDEX
    Explanations

    your article

    np_acts-logits-general · gemini-2.5-flash-lite

    for bad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दिर
    0.42
    माग
    0.40
     مايو
    0.40
     ಕಳೆದ
    0.40
     گلوکار
    0.39
     basi
    0.39
    ጨማሪ
    0.39
     আমাদেরকে
    0.38
     मेला
    0.38
     Böyle
    0.38
    POSITIVE LOGITS
    curl
    0.42
    iman
    0.40
    ve
    0.39
     curl
    0.39
     Cairns
    0.39
    cnx
    0.38
    curvature
    0.37
    stalk
    0.37
     brown
    0.36
    world
    0.36
    Act Density 0.001%

    No Known Activations