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

    Neuronpedia

    INDEX
    Explanations

    nouns and words related to roles within organizations and systems

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

    groups of people or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hom
    -0.31
     thick
    -0.31
     frame
    -0.30
     CiNii
    -0.27
     собе
    -0.26
     screen
    -0.26
     rather
    -0.26
     patch
    -0.25
     cursor
    -0.25
     symbol
    -0.24
    POSITIVE LOGITS
     propOrder
    0.77
     surla
    0.72
     CreateTagHelper
    0.69
    цездатний
    0.68
     zuſammen
    0.68
    сылкі
    0.65
     wiſſen
    0.63
    ſelben
    0.62
     ſehr
    0.62
    tagHelperRunner
    0.62
    Act Density 0.640%

    No Known Activations