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

    Neuronpedia

    INDEX
    Explanations

    copy and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BySize
    0.34
    Copy
    0.33
     evita
    0.32
    copy
    0.31
     cạnh
    0.31
    Grazie
    0.31
    ToServer
    0.30
    CopyTo
    0.30
    aunque
    0.30
     copie
    0.29
    POSITIVE LOGITS
     Ghan
    0.35
     conversely
    0.34
     Indien
    0.33
     adenine
    0.32
     kasus
    0.32
     καὶ
    0.32
     Ghana
    0.31
     Amend
    0.31
     entsprechenden
    0.31
     rector
    0.31
    Act Density 0.002%

    No Known Activations