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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity and belonging within groups

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

    one of the/those X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -0.43
    themselves
    -0.42
     disponibilités
    -0.41
    CharacterOffset
    -0.39
    engertian
    -0.38
     amoureux
    -0.38
     integridad
    -0.37
     cherchés
    -0.37
     saveiro
    -0.36
     پرداخت
    -0.36
    POSITIVE LOGITS
    AccessorTable
    0.52
    transQ
    0.50
    CppMethod
    0.44
    
    0.43
    interopRequire
    0.40
     كومونز
    0.40
     eup
    0.39
     scanf
    0.38
    canf
    0.38
    luck
    0.37
    Act Density 0.189%

    No Known Activations