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

    Neuronpedia

    INDEX
    Explanations

    self-closing HTML tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sanciones
    -0.49
    URBANA
    -0.45
    likler
    -0.41
     autorité
    -0.41
     Behör
    -0.41
    testify
    -0.41
    出版年
    -0.40
     Administrativna
    -0.39
    ⚐
    -0.39
    critic
    -0.38
    POSITIVE LOGITS
    }/>
    1.30
    }}/>
    0.96
    '/>
    0.91
    "/>
    0.84
    }></
    0.84
    "/>
    0.76
     />
    0.73
     />
    0.72
     />\
    0.71
    =""/>
    0.71
    Act Density 0.001%

    No Known Activations