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

    Neuronpedia

    INDEX
    Explanations

    logical operators and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")+
    -0.11
    =""/>\n
    -0.09
    stras
    -0.09
     Weld
    -0.09
    >({
    -0.09
    anki
    -0.09
     }};\n
    -0.08
    ()))č\n
    -0.08
    (){}\n
    -0.08
    ))+
    -0.08
    POSITIVE LOGITS
     &&
    0.24
     ||
    0.22
     {\n
    0.17
    )
    0.17
    ){\n
    0.17
     ||\n
    0.17
     &&\n
    0.15
    '){\n
    0.13
     &
    0.12
     {\n\n
    0.12
    Act Density 0.036%

    No Known Activations