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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ha
    0.41
     XXI
    0.39
     ഹ
    0.38
     h
    0.38
    ायर
    0.38
     hata
    0.37
    जव
    0.37
     svo
    0.37
     H
    0.37
    orestation
    0.36
    POSITIVE LOGITS
    ccd
    0.44
    bb
    0.42
    fff
    0.42
    db
    0.40
    𝑏
    0.40
    ccc
    0.40
    ced
    0.40
    aabb
    0.39
    cfe
    0.39
    Db
    0.39
    Act Density 0.001%

    No Known Activations