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

    Neuronpedia

    INDEX
    Explanations

    Asking questions

    np_max-act · gemini-2.0-flash

    The neuron activates whenever the text contains the verb “ask.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    محمد
    -0.07
    равиль
    -0.07
    Too
    -0.07
    ่ย
    -0.06
     техничес
    -0.06
     fabrics
    -0.06
     Stern
    -0.06
    ware
    -0.06
     blink
    -0.06
     Benjamin
    -0.06
    POSITIVE LOGITS
     discounted
    0.06
     Letters
    0.06
     vás
    0.06
    DNS
    0.06
    napshot
    0.06
     correction
    0.06
     Differences
    0.06
    史
    0.05
     Score
    0.05
    SH
    0.05
    Act Density 0.041%

    No Known Activations