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

    Neuronpedia

    INDEX
    Explanations

    links and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2200>
    0.43
     pretreatment
    0.42
     开
    0.42
    ｽ
    0.40
     الرغم
    0.37
    <unused2171>
    0.37
     backpacking
    0.36
    াতাড়ি
    0.36
    🤺
    0.35
     mastectomy
    0.35
    POSITIVE LOGITS
     (
    0.54
    %,
    0.44
    Für
    0.43
     sendo
    0.39
    a
    0.39
    <h2>
    0.38
     übrigens
    0.38
    ul
    0.38
     junto
    0.37
    ி
    0.37
    Act Density 1.848%

    No Known Activations