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

    Neuronpedia

    INDEX
    Explanations

    the world and geopolitical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    0.46
    ↵
    0.44
     Find
    0.42
     THE
    0.41
     contro
    0.39
     _
    0.38
     Your
    0.37
     question
    0.37
     default
    0.36
     Article
    0.36
    POSITIVE LOGITS
    物联网
    0.38
    𝘔
    0.37
    ombe
    0.36
    पृथ्वी
    0.36
    ૄ
    0.35
    Healing
    0.34
    毁灭
    0.34
    🌙
    0.33
     mennesker
    0.33
    지를
    0.33
    Act Density 0.061%

    No Known Activations