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

    Neuronpedia

    INDEX
    Explanations

    json objects and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    -2.02
    :✨
    -1.99
    ”-
    -1.90
    ”,
    -1.87
    >
    -1.85
    ’
    -1.82
    self
    -1.81
    袮
    -1.80
    ,’
    -1.80
    .”
    -1.75
    POSITIVE LOGITS
    \
    2.13
     {
    2.02
    いえば
    1.95
    1.91
    intelligible
    1.81
    箧
    1.81
     Weltkrieg
    1.79
    頃は
    1.77
     \"
    1.71
     Вода
    1.70
    Act Density 0.029%

    No Known Activations