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

    Neuronpedia

    INDEX
    Explanations

    but are not limited to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    side
    0.42
    moment
    0.42
    esque
    0.41
     jamais
    0.38
     realmente
    0.37
    Perspective
    0.37
     எதுவும்
    0.37
    noe
    0.37
    noop
    0.36
    west
    0.36
    POSITIVE LOGITS
    但不
    0.55
     overlaps
    0.51
     중요한
    0.48
     중요
    0.47
     overlap
    0.46
    嚴重
    0.46
    重要な
    0.46
    สำคัญ
    0.45
     intersecting
    0.44
    严重的
    0.44
    Act Density 0.005%

    No Known Activations