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

    Neuronpedia

    INDEX
    Explanations

    Chinese names and terms related to art and cultural figures

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

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.64
     незавершена
    -0.61
    Datuak
    -0.60
     nakalista
    -0.59
     lenker
    -0.58
     gyhoeddwyd
    -0.56
    ьажоргаш
    -0.56
     ligiloj
    -0.54
    ྑ
    -0.54
    tares
    -0.53
    POSITIVE LOGITS
     perfectamente
    0.42
    riwal
    0.35
     riuscito
    0.34
     Sosten
    0.34
     reconocidos
    0.32
    เฉ
    0.32
     reconocido
    0.32
     enamorado
    0.32
     convertido
    0.31
     symbole
    0.31
    Act Density 0.006%

    No Known Activations