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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming or scripting functions

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    html closing tags and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.85
     Baillargeon
    -0.85
     pleaſure
    -0.82
     Anſ
    -0.81
     ComVisible
    -0.79
     Majefty
    -0.79
     itſelf
    -0.78
    ^(@)
    -0.77
    SharedDtor
    -0.77
     насељу
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.75
    ↵
    0.69
    \{\\
    0.57
    </h3>
    0.52
    </h5>
    0.48
    </blockquote>
    0.47
    ↵↵↵
    0.46
     se
    0.46
    se
    0.46
    </h4>
    0.44
    Act Density 0.105%

    No Known Activations