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

    Neuronpedia

    INDEX
    Explanations

    symbolic links or ports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.53
    V
    0.53
    g
    0.49
    ↵↵
    0.47
    is
    0.46
    卡
    0.45
     V
    0.42
    G
    0.42
    S
    0.42
    R
    0.41
    POSITIVE LOGITS
    যথ
    0.52
    ధ్య
    0.51
    getMetering
    0.48
    یث
    0.47
    يبقى
    0.47
    хих
    0.47
     scientifiques
    0.46
    revalidator
    0.46
    );*/
    0.46
    োদ্ধ
    0.46
    Act Density 0.003%

    No Known Activations