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

    Neuronpedia

    INDEX
    Explanations

    tables and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.79
    ки
    1.48
     in
    1.34
    يل
    1.32
    و
    1.29
    ла
    1.24
    يت
    1.24
    も
    1.21
    ни
    1.20
    يمكن
    1.20
    POSITIVE LOGITS
     I
    1.02
    s
    0.98
    یی
    0.97
     a
    0.96
    -
    0.96
     coalgebra
    0.91
     promov
    0.91
    त्मक
    0.89
    нус
    0.89
    at
    0.88
    Act Density 0.010%

    No Known Activations