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

    Neuronpedia

    INDEX
    Explanations

    verb "to be"

    np_max-act · gemini-2.0-flash

    The neuron is keyed to capitalized named entities—especially software, tools, libraries, or game titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _pos
    -0.07
     Nathan
    -0.07
    Inv
    -0.06
    ondon
    -0.06
    建设
    -0.06
    De
    -0.06
    Pos
    -0.06
     معروف
    -0.06
    .ctx
    -0.05
    ;|
    -0.05
    POSITIVE LOGITS
    ‬
    0.07
     milfs
    0.07
      
↵
↵
    0.07
    CustomLabel
    0.07
    　r
    0.07
    使
    0.07
     принадлеж
    0.06
     embry
    0.06
    *A
    0.06
     
↵ 
↵
    0.06
    Act Density 0.109%

    No Known Activations