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

    Neuronpedia

    INDEX
    Explanations

    tikz, border=5mm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蛮
    0.36
    ayvachi
    0.34
     selectTable
    0.29
    brought
    0.29
    йом
    0.28
     travelled
    0.28
     learnt
    0.28
     sacchar
    0.28
    STS
    0.28
     attravers
    0.27
    POSITIVE LOGITS
     ,
    0.46
    ,
    0.38
     ],
    0.35
    =?,
    0.33
    embre
    0.33
     ،
    0.32
    ++,
    0.32
    ,,
    0.32
    🚔
    0.32
    ।,
    0.31
    Act Density 0.001%

    No Known Activations