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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash

    This neuron fires on capitalized names and titles (proper nouns), especially book and series titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    KP
    -0.07
     }
↵
↵
↵
↵
    -0.07
     anth
    -0.06
     INTERN
    -0.06
     TIME
    -0.06
    edula
    -0.06
    	alert
    -0.06
    龍
    -0.06
    ADR
    -0.06
     표
    -0.06
    POSITIVE LOGITS
     eslint
    0.07
    _EV
    0.07
     Albums
    0.06
    -induced
    0.06
     subtree
    0.06
    (quantity
    0.06
     프로그램
    0.06
    ,data
    0.06
     register
    0.06
    ическая
    0.06
    Act Density 0.025%

    No Known Activations