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

    Neuronpedia

    INDEX
    Explanations

    technical documentation and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     P
    0.66
     N
    0.62
     C
    0.61
     D
    0.59
     R
    0.59
     Z
    0.59
     B
    0.58
     S
    0.58
     V
    0.58
     M
    0.57
    POSITIVE LOGITS
    Gosudarstvennyj
    0.54
     människor
    0.52
    人々
    0.45
     adhipp
    0.43
     rupani
    0.42
     pelayanan
    0.42
    GEBURTS
    0.41
    Gesellschaft
    0.41
     interesses
    0.40
    を通じて
    0.40
    Act Density 0.001%

    No Known Activations