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

    Neuronpedia

    INDEX
    Explanations

    appearance and quality descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ruch
    0.46
    try
    0.45
    We
    0.43
    orestation
    0.42
    '^
    0.41
     ثم
    0.40
    req
    0.40
     مستقبل
    0.40
    RECT
    0.39
     भुजा
    0.39
    POSITIVE LOGITS
    द्दीन
    0.49
     describ
    0.47
     newlyweds
    0.47
    გრამ
    0.45
     tragic
    0.44
     حسین
    0.44
     gothic
    0.43
     கல்லற
    0.43
    МИ
    0.43
    诒
    0.43
    Act Density 0.006%

    No Known Activations