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

    Neuronpedia

    INDEX
    Explanations

    occurrences of empty string declarations or initializations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addContainerGap
    -0.54
    Datuak
    -0.48
    )}
    -0.47
     brotherhood
    -0.47
     })
    -0.45
    τουργ
    -0.44
     AssemblyProduct
    -0.44
     affairs
    -0.43
    SuppressMessage
    -0.43
    })
    -0.43
    POSITIVE LOGITS
     '';
    1.45
     "";
    1.32
     '';
    1.10
    ="";
    1.04
     "";
    1.02
     @"";
    0.97
    ("");
    0.93
    "";
    0.88
    ='';
    0.84
     [];
    0.81
    Act Density 0.005%

    No Known Activations