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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and self-concept

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

    reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.68
     propOrder
    -0.65
    writeFieldEnd
    -0.64
    tonode
    -0.62
     protoimpl
    -0.60
     चीज़ों
    -0.60
    jspb
    -0.52
    rrggbb
    -0.52
     AssemblyTitle
    -0.52
    GraphicsUnit
    -0.51
    POSITIVE LOGITS
     themselves
    0.76
     yourself
    0.74
     ourselves
    0.74
     itself
    0.71
     herself
    0.69
     himself
    0.69
    เอง
    0.68
     yourselves
    0.67
    selves
    0.66
     selbst
    0.66
    Act Density 0.055%

    No Known Activations