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

    Neuronpedia

    INDEX
    Explanations

    language related to perception and first impressions

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

    associated with superficial appearances

    np_acts-logits-general · gemini-2.0-flash

    surface appearance and first glance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lieber
    -0.52
    ↵
    -0.51
     préférences
    -0.47
     vál
    -0.46
    сіб
    -0.46
     chave
    -0.45
    详细信息
    -0.45
    (
    -0.45
    anera
    -0.44
    жере
    -0.44
    POSITIVE LOGITS
     outwardly
    1.12
     seeming
    1.11
     apparente
    1.04
    看似
    0.97
     decep
    0.95
     itſelf
    0.95
     seemingly
    0.94
     appearances
    0.93
     outward
    0.91
     Appearances
    0.91
    Act Density 0.177%

    No Known Activations