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

    Neuronpedia

    INDEX
    Explanations

    variable and function definitions related to data processing and context management

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    boolean conditions and checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.62
    ；
    -0.56
     sẻ
    -0.55
    ;
    -0.52
    ”;
    -0.48
    .;
    -0.48
    *;
    -0.47
    ';
    -0.46
    ";
    -0.46
    ’;
    -0.45
    POSITIVE LOGITS
     is
    1.10
     !=
    1.08
     isn
    1.01
     !==
    0.99
     wasn
    0.96
     exists
    0.95
     ==
    0.95
     doesn
    0.91
     contains
    0.89
     has
    0.85
    Act Density 0.189%

    No Known Activations