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

    Neuronpedia

    INDEX
    Explanations

    enumerating lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     created
    0.54
     set
    0.52
     sets
    0.49
     conco
    0.48
     tables
    0.45
     giant
    0.44
    🔯
    0.44
     standalone
    0.43
     partitioned
    0.43
     official
    0.43
    POSITIVE LOGITS
     Inoltre
    0.58
    Ofer
    0.56
    Otros
    0.55
    Other
    0.55
     อื่น
    0.54
    Ther
    0.53
    However
    0.53
     Nên
    0.53
    anmoins
    0.53
    Ainsi
    0.53
    Act Density 2.041%

    No Known Activations