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

    Neuronpedia

    INDEX
    Explanations

    terms related to community and collaboration

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

    Follows nouns that are time measurements

    np_acts-logits-general · gemini-2.0-flash

    … punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ``
    -1.55
     &#
    -1.26
    ``
    -1.25
    -1.20
     ​
    -1.19
     ‐
    -1.19
     
    -1.13
     $^{\
    -1.12
    ‑
    -1.11
     .....
    -1.10
    POSITIVE LOGITS
    …
    2.82
    )…
    2.07
    …"
    1.92
    "…
    1.92
    ,…
    1.84
    …(
    1.82
    …)
    1.81
    ?…
    1.80
    ”…
    1.79
    …?
    1.78
    Act Density 0.153%

    No Known Activations