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

    Neuronpedia

    INDEX
    Explanations

    multi-head attention queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лт
    0.44
     लालू
    0.42
    ccnc
    0.42
     vutta
    0.42
     bû
    0.42
    captcha
    0.41
     कप
    0.41
    endeu
    0.40
    нению
    0.40
     постепен
    0.40
    POSITIVE LOGITS
     scaled
    0.61
     Queries
    0.61
     queries
    0.57
    Queries
    0.55
     query
    0.54
    Scaled
    0.53
    queries
    0.53
    Query
    0.52
     Query
    0.51
     Scal
    0.49
    Act Density 0.020%

    No Known Activations