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

    Neuronpedia

    INDEX
    Explanations

    |

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لی
    1.55
     histórias
    1.43
    螅
    1.37
     abogado
    1.35
    ਟਰ
    1.35
    НЫ
    1.34
    ९
    1.33
     nagyobb
    1.32
     institución
    1.31
    trashItem
    1.31
    POSITIVE LOGITS
    a
    2.11
     that
    1.98
     a
    1.91
    :
    1.91
     the
    1.88
    ,
    1.84
     which
    1.75
     this
    1.73
    .
    1.72
    '
    1.55
    Act Density 0.214%

    No Known Activations