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

    Neuronpedia

    INDEX
    Explanations

    needs

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of filtering or specification criteria (e.g. “filters,” “specific,” “needs”) used to tailor recommendations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	REQUIRE
    -0.07
    PLICATE
    -0.07
    encrypt
    -0.07
     reluctantly
    -0.07
    ▍
    -0.06
     theaters
    -0.06
    (Result
    -0.06
     đường
    -0.06
    laces
    -0.06
     OnePlus
    -0.06
    POSITIVE LOGITS
    ardy
    0.07
    .UR
    0.06
     Workflow
    0.06
     gri
    0.06
    _pdu
    0.06
    856
    0.06
     blasts
    0.06
     twitch
    0.06
    _lon
    0.06
    AMI
    0.06
    Act Density 0.001%

    No Known Activations