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

    Neuronpedia

    INDEX
    Explanations

    combinations of punctuation and formatting elements in textual content

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

    Comes before citations or bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     greateſt
    -0.83
     myſelf
    -0.82
     Jefus
    -0.79
     itſelf
    -0.77
     GenerationType
    -0.75
    __":
    -0.75
     Normdatei
    -0.75
     themſelves
    -0.73
     Monfieur
    -0.72
    aarrggbb
    -0.72
    POSITIVE LOGITS
    MENAFN
    0.69
    atisk
    0.58
    Diwedd
    0.49
    Predecesor
    0.48
    </td>
    0.48
    سر
    0.47
    ↵↵↵↵↵
    0.46
     вое
    0.46
     disambiguazione
    0.46
    Filmografia
    0.45
    Act Density 0.861%

    No Known Activations