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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     At
    -0.07
    KeyCode
    -0.07
     Negro
    -0.07
     من
    -0.06
     status
    -0.06
     music
    -0.06
     htonl
    -0.06
    .Red
    -0.06
     In
    -0.06
    ཅ
    -0.06
    POSITIVE LOGITS
    פיל
    0.08
    posting
    0.07
    Dup
    0.07
     sophisticated
    0.07
     D
    0.07
    -bal
    0.07
     duplicates
    0.07
     questionable
    0.07
     Daly
    0.07
     descr
    0.06
    Act Density 0.645%

    No Known Activations