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

    Neuronpedia

    INDEX
    Explanations

    Locations or enclosed spaces

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of physical locations (room or area names) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ecycle
    -0.07
    arak
    -0.06
    bp
    -0.06
    _ts
    -0.06
     handlers
    -0.06
    ervlet
    -0.06
    approve
    -0.06
     lidi
    -0.06
    êtes
    -0.06
    thic
    -0.06
    POSITIVE LOGITS
    NdEx
    0.06
    vsp
    0.06
    .getColumn
    0.06
     си
    0.06
    ricula
    0.06
    ôt
    0.06
     UserType
    0.06
     dismay
    0.06
     düşman
    0.06
    :::::::
    0.06
    Act Density 0.009%

    No Known Activations