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

    Neuronpedia

    INDEX
    Explanations

    nuclear energy and weapons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    号码
    0.67
    渐渐
    0.56
    填写
    0.52
    经常
    0.52
     Workspace
    0.52
     该
    0.52
     时尚
    0.52
    掎
    0.52
    广告
    0.52
    语音
    0.52
    POSITIVE LOGITS
     nuclear
    1.48
     uranium
    1.35
     IAEA
    1.31
    nuclear
    1.30
     plutonium
    1.30
     reactor
    1.26
     reactors
    1.23
    Nuclear
    1.22
     Nuclear
    1.19
     neutron
    1.16
    Act Density 0.110%

    No Known Activations