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

    Neuronpedia

    INDEX
    Explanations

    Risk/danger

    np_max-act · gemini-2.0-flash

    The neuron detects terms and phrases related to suicide—especially expressions of suicidal intent, risk factors, assessment, and prevention or intervention steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    fection
    -0.07
     surviving
    -0.06
    ins
    -0.06
     perfect
    -0.06
     FTP
    -0.06
     seats
    -0.06
    ِين
    -0.06
    ala
    -0.06
     seat
    -0.06
     adjusted
    -0.06
    POSITIVE LOGITS
     DataContext
    0.07
    paren
    0.07
     cà
    0.06
    하며
    0.06
    Чер
    0.06
    agnost
    0.06
    .hot
    0.06
    PHPExcel
    0.06
    lerin
    0.06
     birkaç
    0.06
    Act Density 0.018%

    No Known Activations