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

    Neuronpedia

    INDEX
    Explanations

    function arguments in docstrings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    전
    0.73
     م
    0.68
     peaks
    0.67
     ma
    0.66
     multi
    0.65
     કરી
    0.64
     Desk
    0.64
     র
    0.64
     Multi
    0.64
     desk
    0.63
    POSITIVE LOGITS
     hemisphere
    0.63
    semester
    0.63
    帝国
    0.62
    idis
    0.61
    ாஹ்
    0.61
    চি
    0.61
     Semester
    0.60
    畳
    0.59
     semester
    0.59
     الاخير
    0.57
    Act Density 0.114%

    No Known Activations