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

    Neuronpedia

    INDEX
    Explanations

    "New" followed by place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    0.39
     angular
    0.38
    ករណ៍
    0.37
     expose
    0.37
     неизвест
    0.36
     VARCHAR
    0.36
     unknown
    0.35
    Unknown
    0.35
    vili
    0.35
    wise
    0.35
    POSITIVE LOGITS
     York
    0.80
     Zealand
    0.79
     New
    0.73
     Orleans
    0.71
     Jersey
    0.68
     Yorker
    0.67
    York
    0.66
    New
    0.66
     Delhi
    0.65
     নিউ
    0.64
    Act Density 0.023%

    No Known Activations