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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with programming code

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

    Code snippets with numbers and letters

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.55
     rectification
    -0.52
    BASEPATH
    -0.52
    jaja
    -0.52
    ruptedException
    -0.49
    Secondly
    -0.49
    æus
    -0.49
    HasKey
    -0.48
     Narrow
    -0.48
    Välislingid
    -0.47
    POSITIVE LOGITS
    ')));
    0.80
    ')),
    0.77
    ())),
    0.76
    ंदीखरीदारी
    0.74
    ")),
    0.74
    '));
    0.74
    ")));
    0.73
    ']));
    0.72
    ']],
    0.71
    ']))
    0.70
    Act Density 0.134%

    No Known Activations