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

    Neuronpedia

    INDEX
    Explanations

    Indonesian suffixes and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹰ
    0.58
     matroid
    0.57
     Palaiseau
    0.55
     CCSDT
    0.54
     discourse
    0.54
    Singolare
    0.53
    髗
    0.53
    硣
    0.53
    ᓚ
    0.52
    サスカ
    0.52
    POSITIVE LOGITS
    akan
    0.94
    angan
    0.88
    ang
    0.84
    ukan
    0.84
    aran
    0.74
    kan
    0.72
    asan
    0.72
    ak
    0.71
    ikan
    0.71
    ap
    0.70
    Act Density 0.001%

    No Known Activations