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

    Neuronpedia

    INDEX
    Explanations

    lists separated by `/`, `,`, or `or`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৃ
    0.29
    örungen
    0.25
    ⦕
    0.25
    ScienceStudent
    0.23
     UserDefaults
    0.23
     outwe
    0.22
     ανθρώ
    0.22
    唇
    0.22
    aaaaaaaa
    0.22
    OpportunitiesBy
    0.22
    POSITIVE LOGITS
     N
    0.30
     ఇతర
    0.29
     G
    0.28
     other
    0.28
     V
    0.28
     D
    0.27
     S
    0.26
     autres
    0.25
     K
    0.24
     andere
    0.24
    Act Density 0.878%

    No Known Activations