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

    Neuronpedia

    INDEX
    Explanations

    LaTeX and math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .readlines
    -0.08
    _func
    -0.08
     النمو
    -0.08
     downloads
    -0.08
     рабоч
    -0.08
     оф
    -0.08
    _channels
    -0.08
     الوظ
    -0.08
     الموارد
    -0.08
    _download
    -0.07
    POSITIVE LOGITS
     equality
    0.09
    Equality
    0.09
     inequality
    0.08
     concours
    0.08
     pinnacle
    0.08
     maximizing
    0.08
    励
    0.08
     최고
    0.08
     plateau
    0.08
     maxime
    0.08
    Act Density 0.048%

    No Known Activations