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

    Neuronpedia

    INDEX
    Explanations

    Places in Japan/Borneo

    np_max-act · gemini-2.0-flash

    The neuron flags tokens that are part of geographic place names (e.g. regions, islands, prefectures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     assistir
    -0.07
    _rad
    -0.06
    licing
    -0.06
    mpeg
    -0.06
    .signature
    -0.06
     electronically
    -0.06
     swamp
    -0.06
     northwest
    -0.06
    Methods
    -0.06
     Indexed
    -0.06
    POSITIVE LOGITS
    agascar
    0.07
     bluff
    0.07
    264
    0.06
     getattr
    0.06
     proto
    0.06
     ),↵
    0.06
    reload
    0.06
     therapist
    0.06
                        ↵                    ↵
    0.06
    わ
    0.06
    Act Density 0.013%

    No Known Activations