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

    Neuronpedia

    INDEX
    Explanations

    references to user-related concepts and identifiers

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

    user related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.51
    great
    -0.49
    Fordítás
    -0.48
    jelaskan
    -0.46
    rouvez
    -0.45
     anúncio
    -0.44
    AddRange
    -0.44
    ềm
    -0.44
    adds
    -0.44
    fine
    -0.43
    POSITIVE LOGITS
     Usuario
    0.98
     usuario
    0.90
    usuario
    0.81
    Usuario
    0.80
    updateUser
    0.73
     updateUser
    0.71
     Usuarios
    0.68
     userModel
    0.67
     userType
    0.67
    userList
    0.66
    Act Density 0.001%

    No Known Activations