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

    Neuronpedia

    INDEX
    Explanations

    structured code or data references

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

    Code or text mentioning lists or strings

    np_acts-logits-general · gemini-2.0-flash

    list operations and data manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )";
    -1.17
     />";
    -1.08
     ་་
    -1.07
     $_"
    -1.06
    )");
    -1.03
    )”.
    -1.02
     />';
    -1.02
    .";
    -1.02
     ―――――
    -1.01
     ")");
    -0.98
    POSITIVE LOGITS
      
    0.85
     String
    0.70
    ↵
    0.68
     string
    0.65
     user
    0.63
     array
    0.63
     data
    0.61
     values
    0.60
     it
    0.58
     
    0.58
    Act Density 0.938%

    No Known Activations