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

    Neuronpedia

    INDEX
    Explanations

    Room

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “room” (and its variants) and associated room‐detail tokens in hotel reviews.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tracks
    -0.07
    bindings
    -0.07
     isim
    -0.06
    _MANAGER
    -0.06
     editors
    -0.06
    Constraints
    -0.06
    IAM
    -0.06
    typeName
    -0.06
     hoàng
    -0.06
    шло
    -0.06
    POSITIVE LOGITS
     unins
    0.07
     geme
    0.07
     AUT
    0.07
     conventional
    0.07
     Wichita
    0.07
     Zy
    0.07
     Geh
    0.07
     suất
    0.06
    裡
    0.06
     miserable
    0.06
    Act Density 0.009%

    No Known Activations