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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of geographic boundary descriptions, especially phrases indicating what lies to the north, south, east, or west of a place.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ΙΟΥ
    -0.07
    аного
    -0.07
     antigen
    -0.07
     dever
    -0.07
    CO
    -0.06
    _REQ
    -0.06
     요청
    -0.06
     SHALL
    -0.06
     aired
    -0.06
    verts
    -0.06
    POSITIVE LOGITS
    attached
    0.07
    .defaultProps
    0.06
     champ
    0.06
    _notes
    0.06
    .instructions
    0.06
    .diff
    0.06
     drafting
    0.06
     están
    0.06
    ゲーム
    0.06
     farklı
    0.06
    Act Density 0.022%

    No Known Activations