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

    Neuronpedia

    INDEX
    Explanations

    special characters or escape sequences in code or text

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

    LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -0.64
     saw
    -0.51
    </u>
    -0.51
     Bel
    -0.50
     fe
    -0.49
    <sup>
    -0.48
    </strong>
    -0.47
     DEV
    -0.47
     #
    -0.47
     Mag
    -0.47
    POSITIVE LOGITS
    \}\\
    1.08
     itſelf
    0.98
    出版年
    0.97
    verwijspagina
    0.96
     doubtnut
    0.92
    ThroughAttribute
    0.88
    \{\\
    0.88
    portál
    0.87
     pleaſure
    0.87
    ;\\
    0.87
    Act Density 0.039%

    No Known Activations