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

    Neuronpedia

    INDEX
    Explanations

    indicators of data structure and formatting in documents

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

    figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.57
    useNewUrlParser
    -0.50
    OCCURRED
    -0.50
    afficheront
    -0.49
     Italijani
    -0.49
    utilisons
    -0.48
    EndGlobalSection
    -0.48
     centrales
    -0.47
     ujednoznacz
    -0.47
    Vidite
    -0.46
    POSITIVE LOGITS
    endcsname
    0.52
    barco
    0.40
     Descent
    0.39
    stan
    0.39
    wijze
    0.39
    typec
    0.39
    goto
    0.39
    rent
    0.38
    üst
    0.38
    ]].
    0.37
    Act Density 0.704%

    No Known Activations