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

    Neuronpedia

    INDEX
    Explanations

    compatibility

    np_max-act · gemini-2.0-flash

    The neuron is triggered by words used when asking for advice or choices (e.g. “what,” “should,” “do,” “suggestions,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    st
    -0.07
    _CODE
    -0.07
    Javascript
    -0.06
    	account
    -0.06
     induced
    -0.06
    ,password
    -0.06
     fear
    -0.06
     INTERVAL
    -0.06
    सन
    -0.06
     dado
    -0.06
    POSITIVE LOGITS
    ήν
    0.07
     metaData
    0.06
     birthdays
    0.06
    Founder
    0.06
     clk
    0.06
    itag
    0.06
    ΩΣ
    0.06
    .li
    0.06
    =<?
    0.06
    osi
    0.06
    Act Density 0.053%

    No Known Activations