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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gerard
    -0.07
    lament
    -0.07
     authorities
    -0.07
     عبارت
    -0.06
     Leonard
    -0.06
     chví
    -0.06
     gì
    -0.06
     نو
    -0.06
    _backward
    -0.06
    ，他们
    -0.06
    POSITIVE LOGITS
    MAS
    0.06
     propagate
    0.06
    FAULT
    0.06
     vocational
    0.06
    st
    0.06
     △
    0.06
    PackageManager
    0.06
     stati
    0.06
     '${
    0.06
     victory
    0.06
    Act Density 0.009%

    No Known Activations