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

    Neuronpedia

    INDEX
    Explanations

    numerical data, equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Razor
    -0.07
     Grades
    -0.07
     banging
    -0.07
    ़र
    -0.06
    testCase
    -0.06
    APA
    -0.06
    NavigationView
    -0.06
     suç
    -0.06
    UserProfile
    -0.06
    dou
    -0.06
    POSITIVE LOGITS
    .sparse
    0.07
    .future
    0.07
     erotik
    0.07
     minecraft
    0.06
    @gmail
    0.06
    Erot
    0.06
    ">',
    0.06
     میشود
    0.06
     dív
    0.06
     intestinal
    0.06
    Act Density 0.021%

    No Known Activations