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

    Neuronpedia

    INDEX
    Explanations

    Python code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     @
    0.71
    @
    0.71
    &
    0.66
     &
    0.64
     &&
    0.63
    นี้
    0.62
     #
    0.62
     this
    0.61
     if
    0.61
     بهذا
    0.59
    POSITIVE LOGITS
     len
    1.23
    len
    1.14
    int
    0.98
     int
    0.89
    list
    0.88
    列表
    0.86
    Len
    0.84
    <unused1968>
    0.83
    str
    0.83
    dict
    0.81
    Act Density 0.438%

    No Known Activations