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

    Neuronpedia

    INDEX
    Explanations

    references to authors or contributors in academic or formal writing

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

    authorship or attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ðsíða
    -0.71
    arangay
    -0.69
     feroit
    -0.68
    ientras
    -0.66
     avoient
    -0.66
    ambién
    -0.65
    kémon
    -0.65
    transQ
    -0.65
    gucig
    -0.62
    ementara
    -0.62
    POSITIVE LOGITS
     AssemblyCompany
    0.56
    by
    0.54
     createdBy
    0.51
    InjectMocks
    0.50
     Mary
    0.46
     Fran
    0.45
     by
    0.44
     Mal
    0.43
     author
    0.43
     Sy
    0.42
    Act Density 0.006%

    No Known Activations