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

    Neuronpedia

    INDEX
    Explanations

    mostly numbers and punctuation, possibly within citations

    oai_token-act-pair · gemini-2.0-flash

    mixed content or code-like expressions

    np_token-act-pair-logits · gpt-4o-mini

    Citations, statistics, and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPATH
    -0.52
    
    -0.47
    +:+
    -0.46
    RUnlock
    -0.45
    Bear
    -0.44
    naeus
    -0.44
    bear
    -0.43
     bear
    -0.43
    Liber
    -0.41
    oplasma
    -0.41
    POSITIVE LOGITS
    出版年
    0.73
     otomatig
    0.64
    Abitanti
    0.62
    נטרנט
    0.60
    __':
    0.59
    PECT
    0.58
    elry
    0.57
    iocene
    0.54
    newInstance
    0.53
    ardos
    0.53
    Act Density 3.637%

    No Known Activations