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

    Neuronpedia

    INDEX
    Explanations

    Valerius Thorne

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ך
    1.23
    会
    1.19
    力が
    1.02
    (“
    0.96
    ০০
    0.96
    (
    0.96
    köy
    0.95
    ได้
    0.94
    ેલ
    0.91
    會
    0.91
    POSITIVE LOGITS
    ه
    1.37
    ה
    1.36
    a
    1.33
    ت
    1.14
    ق
    1.09
    הר
    0.97
    ا
    0.97
    া
    0.96
    ע
    0.94
     amelyek
    0.93
    Act Density 0.000%

    No Known Activations