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

    Neuronpedia

    INDEX
    Explanations

    references to health risks and legal implications surrounding medical conditions

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

    that introduce a statement or conclusion

    np_acts-logits-general · gemini-2.0-flash

    according to research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    afficheront
    -0.58
    });
    -0.56
     ivelany
    -0.55
    arranty
    -0.54
    ')}}">
    -0.53
     Efq
    -0.53
    enumii
    -0.52
    ]]
    -0.52
    "]));
    -0.52
    )•
    -0.51
    POSITIVE LOGITS
     according
    2.45
    according
    2.07
     According
    1.99
    According
    1.98
     ifølge
    1.91
     selon
    1.86
     reportedly
    1.85
     volgens
    1.85
     según
    1.83
     menurut
    1.77
    Act Density 0.720%

    No Known Activations