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

    Neuronpedia

    INDEX
    Explanations

    political and visual descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     інших
    0.41
    athermy
    0.40
     desorption
    0.39
     ಇತರ
    0.39
     swapping
    0.39
    可能
    0.38
    出荷
    0.37
     vanishes
    0.37
    长度
    0.36
     можуть
    0.36
    POSITIVE LOGITS
     principled
    0.50
    political
    0.44
     Governance
    0.42
    Governance
    0.42
     principles
    0.42
     political
    0.41
     politič
    0.40
     genuinely
    0.40
    лянчук
    0.39
     ethical
    0.38
    Act Density 0.002%

    No Known Activations