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

    Neuronpedia

    INDEX
    Explanations

    code following source and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entemente
    0.38
     भोज
    0.37
    σταν
    0.36
    کنش
    0.35
    onio
    0.34
    oplasmic
    0.34
    ﺄ
    0.34
    ഷ്ട്ര
    0.33
    celli
    0.33
    ✫
    0.33
    POSITIVE LOGITS
     code
    4.25
    code
    3.80
    コード
    3.69
     कोड
    3.64
     Code
    3.63
     código
    3.63
     код
    3.59
    Code
    3.56
     codes
    3.55
     코드
    3.48
    Act Density 0.399%

    No Known Activations