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

    Neuronpedia

    INDEX
    Explanations

    references to Western-related terms and concepts

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

    following "Western" or "eastern"

    np_acts-logits-general · gemini-2.0-flash

    Western Hemisphere, Australia, Pacific, Blot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.60
     fapt
    -0.57
     Roskov
    -0.56
     ComVisible
    -0.54
     définiti
    -0.54
     Normdatei
    -0.52
    Secondly
    -0.50
    iseite
    -0.49
     culoare
    -0.49
    UnknownFieldSet
    -0.49
    POSITIVE LOGITS
    most
    0.87
    ized
    0.86
    IZER
    0.77
    ization
    0.74
    MOST
    0.73
     hemisphere
    0.72
     Hemisphere
    0.71
    ers
    0.68
    izer
    0.65
    ilien
    0.64
    Act Density 0.091%

    No Known Activations