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

    Neuronpedia

    INDEX
    Explanations

    islands/archipelagos

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific geographic place names—especially island and atoll names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lawn
    -0.07
    _guest
    -0.07
    .Password
    -0.07
    。不过
    -0.06
    γμα
    -0.06
    _NEAREST
    -0.06
     prepares
    -0.06
    /parser
    -0.06
    (artist
    -0.06
    umbotron
    -0.06
    POSITIVE LOGITS
    agos
    0.07
     vrij
    0.07
    ผม
    0.06
    Away
    0.06
     Bahamas
    0.06
     
    0.06
    idend
    0.06
    ORAGE
    0.06
     choked
    0.06
     Kimber
    0.06
    Act Density 0.011%

    No Known Activations