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

    Neuronpedia

    INDEX
    Explanations

    code explanations and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    th
    2.45
    2.41
    als
    2.31
    ย์
    2.23
    ところ
    2.04
    "",
    2.02
    ${
    1.98
    Ûn
    1.98
    acter
    1.98
    tt
    1.94
    POSITIVE LOGITS
    an
    2.80
    𝐘
    2.67
    ان
    2.55
    ल
    2.51
     ounce
    2.51
     slam
    2.48
     GAO
    2.44
    𐰣
    2.39
    ي
    2.39
     austenite
    2.38
    Act Density 0.045%

    No Known Activations