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

    Neuronpedia

    INDEX
    Explanations

    health or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     back
    0.66
    自身の
    0.66
     level
    0.64
     most
    0.63
    د
    0.62
    fiz
    0.61
     hidden
    0.61
     מק
    0.61
     fiz
    0.60
    र्ट
    0.60
    POSITIVE LOGITS
     Federación
    1.02
    éseket
    0.97
     Stry
    0.94
    isać
    0.91
     maniak
    0.90
    arakhand
    0.89
    代引き
    0.88
    hattisgarh
    0.88
     glorie
    0.88
     necesitas
    0.88
    Act Density 0.006%

    No Known Activations