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

    Neuronpedia

    INDEX
    Explanations

    XML tags with attributes like name and param

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    though
    0.70
    spl
    0.69
    void
    0.69
    while
    0.66
    €.
    0.65
    ¹.
    0.64
    $('.
    0.64
    Nú
    0.63
    蒾
    0.63
     برگزار
    0.63
    POSITIVE LOGITS
    ></
    1.27
    >
    1.22
    />
    1.22
    ><
    1.17
    >\
    1.12
     />
    1.12
     name
    1.10
     xmlns
    1.09
    >//
    1.02
    >{
    1.01
    Act Density 0.014%

    No Known Activations