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

    Neuronpedia

    INDEX
    Explanations

    commands or functions related to generating content or entities

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

    generating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    topRight
    -0.48
    riwal
    -0.47
    hoben
    -0.45
     Obrador
    -0.44
    aspectj
    -0.44
     varandra
    -0.43
     "..\..\..\
    -0.43
     pageNo
    -0.41
     ControllerBase
    -0.41
     roleId
    -0.41
    POSITIVE LOGITS
    generate
    2.16
     generate
    1.97
    Generate
    1.93
     Generate
    1.88
     generating
    1.55
     generates
    1.55
     Generates
    1.39
     Generating
    1.36
    Generating
    1.35
     GENER
    1.27
    Act Density 0.008%

    No Known Activations