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

    Neuronpedia

    INDEX
    Explanations

    legal, code, and technical documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ریک
    -0.69
    ztyn
    -0.68
    тія
    -0.66
    lateinit
    -0.66
     фигур
    -0.63
     Powers
    -0.63
     seiner
    -0.63
    height
    -0.63
     الانت
    -0.63
     Dar
    -0.62
    POSITIVE LOGITS
    canes
    0.72
    edu
    0.72
     梁
    0.68
    Gestion
    0.66
     perturb
    0.66
    executeUpdate
    0.66
     Sef
    0.66
     gerekiyor
    0.66
    шь
    0.65
    Annotations
    0.65
    Act Density 0.065%

    No Known Activations