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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to the lives of individuals or groups

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

    lives of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isation
    -0.48
    hibition
    -0.44
    적인
    -0.44
    SOUNDBITE
    -0.43
     action
    -0.43
     azione
    -0.43
    entrance
    -0.43
     activity
    -0.43
    ization
    -0.43
    fication
    -0.42
    POSITIVE LOGITS
    UnknownFields
    0.48
     يتيمه
    0.47
    ؤلاء
    0.44
    ỡng
    0.44
     participants
    0.42
     gamers
    0.42
    copyOf
    0.42
     children
    0.42
     people
    0.42
     protoimpl
    0.41
    Act Density 0.052%

    No Known Activations