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

    Neuronpedia

    INDEX
    Explanations

    female perspective

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of flight attendants (or closely related travel-professional terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     coco
    -0.06
    =====↵
    -0.06
    ヘ
    -0.06
    ऊ
    -0.06
    الة
    -0.06
    飲
    -0.06
    Rep
    -0.06
     incorrectly
    -0.05
    ↵            
↵
    -0.05
    ดน
    -0.05
    POSITIVE LOGITS
    .appspot
    0.07
     світі
    0.07
    -hidden
    0.07
    *>*
    0.07
     spiel
    0.07
    _VERIFY
    0.07
    employed
    0.06
     REQUEST
    0.06
     revenue
    0.06
    erusform
    0.06
    Act Density 0.154%

    No Known Activations