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

    Neuronpedia

    INDEX
    Explanations

    identical or same values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    શન
    0.45
    dates
    0.43
    ాల
    0.43
    윅
    0.42
    ານ
    0.42
    mlst
    0.41
    墘
    0.41
    ᆯ
    0.41
    пления
    0.39
    들
    0.39
    POSITIVE LOGITS
     identiques
    0.51
     identical
    0.47
     beide
    0.47
     hetzelfde
    0.46
     alike
    0.46
     gleichen
    0.45
     gleiche
    0.44
     iris
    0.43
     stesso
    0.42
     tiež
    0.42
    Act Density 0.113%

    No Known Activations