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

    Neuronpedia

    INDEX
    Explanations

    diseases and medical concerns

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to medical-treatment terms and risk/benefit language (e.g. procedures like C-section or major surgery, medication names, and discussion of safety/harm).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     simmer
    -0.07
     exposure
    -0.07
     Patrick
    -0.06
     purpos
    -0.06
     conscious
    -0.06
     Roger
    -0.06
     refurbished
    -0.06
    -blind
    -0.06
     Пар
    -0.06
     comeback
    -0.06
    POSITIVE LOGITS
    ));↵↵↵
    0.07
    _VALIDATE
    0.07
    ooky
    0.07
     bitk
    0.07
    =");↵
    0.07
     Abilities
    0.07
    елефон
    0.06
     Yok
    0.06
    pwd
    0.06
    );↵↵↵↵↵
    0.06
    Act Density 0.137%

    No Known Activations