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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mine
    -0.08
    Wizard
    -0.08
    Mine
    -0.08
    _Fe
    -0.08
     sticker
    -0.08
    ารถ
    -0.07
    <'
    -0.07
    stellung
    -0.07
     `'
    -0.07
    ürk
    -0.07
    POSITIVE LOGITS
     hospice
    0.14
     মৃত্য
    0.14
     मृत्यु
    0.13
     મૃત્યુ
    0.13
     মৃত্যু
    0.13
     deaths
    0.12
     മരണ
    0.11
     death
    0.11
     Hospice
    0.11
     died
    0.11
    Act Density 0.026%

    No Known Activations