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

    Neuronpedia

    INDEX
    Explanations

    p-values in statistical results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incarceration
    -0.07
     nhớ
    -0.07
     cz
    -0.06
    /accounts
    -0.06
    疾
    -0.06
     рост
    -0.06
     가지
    -0.06
     gluten
    -0.06
     tog
    -0.06
     readings
    -0.06
    POSITIVE LOGITS
     trail
    0.06
     отримання
    0.06
     misleading
    0.06
     자신의
    0.06
    athroom
    0.06
     म
    0.06
     Mattis
    0.05
    SSF
    0.05
     Yankee
    0.05
    NewUrlParser
    0.05
    Act Density 0.010%

    No Known Activations