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

    Neuronpedia

    INDEX
    Explanations

    place name beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Turing
    0.54
     Shenzhen
    0.54
     Tencent
    0.50
     negatif
    0.48
     overfitting
    0.47
     Xiao
    0.46
     Chengdu
    0.46
     cyberpunk
    0.46
     ChatGPT
    0.46
     Xu
    0.46
    POSITIVE LOGITS
     oaks
    0.61
     Oaks
    0.59
    wood
    0.58
    ristown
    0.58
     Creek
    0.57
     hickory
    0.57
    woods
    0.57
     hardwoods
    0.56
    estown
    0.54
    WOOD
    0.54
    Act Density 0.015%

    No Known Activations