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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash

    This neuron detects bibliographic metadata lines—specifically “Received,” “accepted,” and related date fields in academic paper headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    blood
    -0.07
     갈
    -0.06
    Bien
    -0.06
    未
    -0.06
    атів
    -0.06
     حال
    -0.06
    	ds
    -0.06
     [[]
    -0.06
    ยน
    -0.06
    答
    -0.06
    POSITIVE LOGITS
     Comparable
    0.06
    larınız
    0.06
     تجه
    0.06
    .OrdinalIgnoreCase
    0.06
    enames
    0.06
     �
    0.06
     веществ
    0.06
    -created
    0.06
     configur
    0.06
    рование
    0.06
    Act Density 0.003%

    No Known Activations