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

    Neuronpedia

    INDEX
    Explanations

    legal consequences or getting caught

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teaspoons
    0.36
     calyce
    0.35
     indium
    0.35
     hydrating
    0.34
     hydrated
    0.34
     utilisez
    0.34
    Configuration
    0.34
     unordered
    0.33
    ()
    0.33
     molybdenum
    0.33
    POSITIVE LOGITS
     persecution
    0.64
    リスク
    0.63
    風險
    0.62
     repercussions
    0.59
     risks
    0.58
     risiko
    0.57
     risk
    0.57
    风险
    0.57
     риск
    0.57
     경찰
    0.56
    Act Density 0.222%

    No Known Activations