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

    Neuronpedia

    INDEX
    Explanations

    Health struggles

    np_max-act · gemini-2.0-flash

    The neuron detects dismissive or minimizing language about mental-health problems that urges simplistic self-control instead of acknowledging real distress.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Bolshevik
    -0.06
    \system
    -0.06
     exemple
    -0.06
     astronomical
    -0.06
     области
    -0.06
    amb
    -0.06
     #=>
    -0.06
     verge
    -0.06
    -Sep
    -0.06
    ricing
    -0.06
    POSITIVE LOGITS
     newspapers
    0.07
    圳
    0.06
    .createStatement
    0.06
     OpCode
    0.06
    Enter
    0.06
    UNT
    0.06
     urged
    0.06
    _candidates
    0.06
    /Branch
    0.06
    ILI
    0.06
    Act Density 0.165%

    No Known Activations