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

    Neuronpedia

    INDEX
    Explanations

    North

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHOW
    -0.09
    Eq
    -0.08
    REAK
    -0.08
     toplant
    -0.08
     раньше
    -0.08
    _-
    -0.08
     possessing
    -0.08
     PASSWORD
    -0.08
    Evt
    -0.08
    Receive
    -0.08
    POSITIVE LOGITS
    大陆
    0.11
     America
    0.10
     continents
    0.10
     América
    0.09
     Americas
    0.09
     Antarctica
    0.08
     अमेरिका
    0.08
     Bahrain
    0.08
     Azerbaijan
    0.08
    Spain
    0.08
    Act Density 0.014%

    No Known Activations