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

    Neuronpedia

    INDEX
    Explanations

    possessive, contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.48
    u
    0.43
    ed
    0.42
    er
    0.36
    at
    0.35
    el
    0.33
    ות
    0.31
    ل
    0.30
    i
    0.30
    ي
    0.30
    POSITIVE LOGITS
    0.34
     iaitu
    0.23
     अक्टूबर
    0.22
     অ
    0.22
     ত
    0.22
    }-\
    0.22
    lié
    0.21
     अप्रैल
    0.21
    낸
    0.20
    <unused354>
    0.20
    Act Density 2.834%

    No Known Activations