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

    Neuronpedia

    INDEX
    Explanations

    Mary Poppins/Willy Wonka

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jeans
    -0.07
     autism
    -0.07
     hiệu
    -0.07
    ="//
    -0.06
     Fraud
    -0.06
     ints
    -0.06
     rapes
    -0.06
    =',
    -0.06
     Rape
    -0.06
    Female
    -0.06
    POSITIVE LOGITS
     remnants
    0.06
    ntag
    0.06
    かって
    0.06
    IEnumerator
    0.06
    airs
    0.06
    ستم
    0.06
    าซ
    0.06
    ुव
    0.06
     наст
    0.05
    ledge
    0.05
    Act Density 0.024%

    No Known Activations