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

    Neuronpedia

    INDEX
    Explanations

    suffering and wounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ridiculous
    0.40
     dehydration
    0.40
    利亚
    0.39
    য়ং
    0.39
    cznym
    0.38
    वी
    0.38
    лишком
    0.38
    ாட
    0.38
    ATL
    0.37
     được
    0.37
    POSITIVE LOGITS
     intuitively
    0.38
     invariable
    0.38
     decorated
    0.37
     seemed
    0.37
     predominant
    0.37
    рных
    0.37
     map
    0.36
     темы
    0.36
     землю
    0.36
     effectually
    0.36
    Act Density 0.003%

    No Known Activations