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

    Neuronpedia

    INDEX
    Explanations

    phrases related to functionality and effectiveness in collaboration

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

    works as intended or like this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.63
    msgTypes
    -0.50
     autorytatywna
    -0.50
     pungkas
    -0.47
    :✨
    -0.44
    SourceChecksum
    -0.44
    ```
    -0.44
     beliau
    -0.43
    期刊论文
    -0.43
    ]")]
    -0.43
    POSITIVE LOGITS
     working
    0.76
    Working
    0.74
    working
    0.65
     Working
    0.63
    WORKING
    0.63
     WORKING
    0.61
    Worked
    0.60
     trabajan
    0.60
     trabajar
    0.60
     worked
    0.60
    Act Density 0.048%

    No Known Activations