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

    Neuronpedia

    INDEX
    Explanations

    references to data analysis and research methodologies

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

    study shows findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.59
    expandindo
    -0.56
     AssemblyVersion
    -0.54
    GEBURTS
    -0.53
     estekak
    -0.51
     мәкал
    -0.51
     linkovi
    -0.50
     nonUne
    -0.49
     Chwiliwch
    -0.48
     שוליים
    -0.47
    POSITIVE LOGITS
     shows
    1.73
     indicates
    1.68
     reveals
    1.60
     indicate
    1.53
     suggests
    1.52
    shows
    1.50
     showed
    1.49
    indicates
    1.41
     menunjukkan
    1.37
     reveal
    1.35
    Act Density 0.614%

    No Known Activations