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

    Neuronpedia

    INDEX
    Explanations

    matrix multiplication vector dot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .,"
    0.40
    0.40
     മൈ
    0.39
    outines
    0.38
    分泌
    0.37
    ,,
    0.36
    、、
    0.35
    mir
    0.35
    ட்ப
    0.35
    ś
    0.34
    POSITIVE LOGITS
    ㈜
    0.43
     usług
    0.42
     株式会社
    0.39
    Sunny
    0.38
    나
    0.38
     conform
    0.37
     lords
    0.37
    ות
    0.37
    게요
    0.37
     Sime
    0.37
    Act Density 0.012%

    No Known Activations