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

    Neuronpedia

    INDEX
    Explanations

    yes/no questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exclusively
    -0.06
    tro
    -0.06
     certificates
    -0.06
    _HINT
    -0.06
    _Unit
    -0.06
     прав
    -0.06
    >↵↵↵↵↵
    -0.06
    .Static
    -0.06
     objects
    -0.06
     invasive
    -0.06
    POSITIVE LOGITS
    .BooleanField
    0.07
    ชน
    0.07
    ={"/
    0.06
     while
    0.06
    _portfolio
    0.06
    ıyor
    0.06
     gerektiğini
    0.06
    ाऊ
    0.06
     conseguir
    0.06
     Enumeration
    0.06
    Act Density 0.004%

    No Known Activations