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

    Neuronpedia

    INDEX
    Explanations

    numerical indices and variables that represent relationships in matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ij indices in math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opgenomen
    -0.64
    AndEndTag
    -0.63
     continúas
    -0.59
     vastaan
    -0.57
     geïsole
    -0.57
    principalTable
    -0.56
     probado
    -0.52
     âmes
    -0.52
     zijne
    -0.51
     asesinado
    -0.51
    POSITIVE LOGITS
    ij
    2.44
    IJ
    1.98
     IJ
    1.70
     ij
    1.68
    iji
    1.20
     Mij
    1.12
     Nij
    1.11
    ijs
    1.11
    ija
    1.10
    ijk
    1.07
    Act Density 0.016%

    No Known Activations