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

    Neuronpedia

    INDEX
    Explanations

    specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aders
    0.62
     стрельца
    0.60
     파인더
    0.57
     산업
    0.55
    퓰
    0.54
    <unused985>
    0.54
     풍
    0.54
     나오고
    0.53
     वायरलेस
    0.53
     전자
    0.53
    POSITIVE LOGITS
    S
    0.46
    C
    0.46
    VER
    0.43
    Car
    0.43
    要
    0.43
    P
    0.43
     y
    0.42
    V
    0.42
    -
    0.40
    strong
    0.40
    Act Density 0.000%

    No Known Activations