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

    Neuronpedia

    INDEX
    Explanations

    action sequence locations

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of specific physical locations or settings (e.g. place names and venue descriptors).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    elt
    -0.07
     Pou
    -0.07
    adv
    -0.06
    &oacute
    -0.06
    Overall
    -0.06
     GROUP
    -0.06
     DV
    -0.06
     करन
    -0.06
     Brid
    -0.06
     Pound
    -0.06
    POSITIVE LOGITS
    addAction
    0.08
    inese
    0.07
    اسات
    0.06
    .setHorizontal
    0.06
     versus
    0.06
    طه
    0.06
    ardy
    0.06
    нед
    0.06
    投
    0.06
    яж
    0.06
    Act Density 0.039%

    No Known Activations