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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the act of initiating or beginning something

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

    start something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     externi
    -0.44
    URIComponent
    -0.36
    esgue
    -0.35
     valueForKey
    -0.35
    WebRequest
    -0.35
     aspek
    -0.35
    quelize
    -0.34
     accommodation
    -0.33
     I
    -0.33
    unicode
    -0.33
    POSITIVE LOGITS
     started
    1.25
    started
    1.24
    Start
    1.20
     Started
    1.20
    Started
    1.19
     start
    1.17
    starts
    1.16
     Starts
    1.15
     starts
    1.14
     Start
    1.13
    Act Density 0.039%

    No Known Activations