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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe personal identities or roles

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

    "I am a" or "as a" phrases

    np_acts-logits-general · gemini-2.0-flash

    i am a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vanske
    -0.55
     termica
    -0.54
    )}
    -0.50
    emplar
    -0.47
    antaranya
    -0.47
    umumkan
    -0.47
     antaranya
    -0.46
    '}}>
    -0.46
     svå
    -0.46
    "}}
    -0.45
    POSITIVE LOGITS
     ſmall
    0.74
     useAppContext
    0.70
     Савезне
    0.67
     myſelf
    0.66
     avid
    0.65
    født
    0.64
     perſon
    0.64
     AspNetCore
    0.64
    glMatrixMode
    0.63
     people
    0.62
    Act Density 0.108%

    No Known Activations