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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beads
    -0.07
    Purple
    -0.07
    NavBar
    -0.06
     가입
    -0.06
     GET
    -0.06
    StreamWriter
    -0.06
    aped
    -0.06
     UserDao
    -0.06
     Particip
    -0.06
    iframe
    -0.06
    POSITIVE LOGITS
     weren
    0.07
    ●
    0.07
     don
    0.06
    IX
    0.06
    俄
    0.06
     догов
    0.06
    сии
    0.06
    clipse
    0.06
    assigned
    0.06
     تحص
    0.06
    Act Density 0.041%

    No Known Activations