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

    Neuronpedia

    INDEX
    Explanations

    Location words

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific geographic place names (e.g. towns, cities, landmarks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Manuals
    -0.08
    Children
    -0.07
     Belt
    -0.07
    phia
    -0.07
    _retry
    -0.07
    Playback
    -0.06
    .Physics
    -0.06
     Header
    -0.06
     belt
    -0.06
     months
    -0.06
    POSITIVE LOGITS
     στο
    0.06
     Professor
    0.06
     estruct
    0.06
    ’ai
    0.06
     στις
    0.06
    /thread
    0.06
     ک
    0.06
     kaynağı
    0.06
     ideological
    0.06
    Bo
    0.06
    Act Density 0.011%

    No Known Activations