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

    Neuronpedia

    INDEX
    Explanations

    across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üglich
    0.41
    两者
    0.37
     ṣe
    0.37
    centerY
    0.35
     Tes
    0.35
     Bundan
    0.35
    筲
    0.35
     Burns
    0.34
    anjutan
    0.34
     phê
    0.34
    POSITIVE LOGITS
     across
    4.25
    across
    4.09
     Across
    3.91
    Across
    3.89
    跨
    1.92
     lintas
    1.44
     spanning
    1.38
     crossing
    1.37
     cross
    1.30
    cross
    1.29
    Act Density 0.085%

    No Known Activations