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

    Neuronpedia

    INDEX
    Explanations

    Introduction

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on the document’s “Introduction” section heading.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    $t
    -0.07
     YYYY
    -0.07
     якій
    -0.07
    梨
    -0.07
    :id
    -0.06
    	Port
    -0.06
     Remix
    -0.06
     Survey
    -0.06
     staining
    -0.06
    บอล
    -0.06
    POSITIVE LOGITS
    ?'↵↵
    0.07
    نامج
    0.06
     юрид
    0.06
    ็ว
    0.06
     نسب
    0.06
     quantidade
    0.06
     misrepresented
    0.06
     regulates
    0.06
    ững
    0.06
     چند
    0.06
    Act Density 0.009%

    No Known Activations