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

    Neuronpedia

    INDEX
    Explanations

    indicators of breaks or inclusions in structured formats, such as programming or technical documentation

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

    Punctuation, code snippets, or uncommon symbols

    np_acts-logits-general · gemini-2.0-flash

    patients and beneficiaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     …
    -0.93
     …)
    -0.87
    ՚
    -0.82
     ….
    -0.81
    …~
    -0.79
     …”
    -0.78
    ſelves
    -0.77
     […]
    -0.76
     …………
    -0.76
     (…)
    -0.76
    POSITIVE LOGITS
    --
    0.74
     --
    0.69
    </h6>
    0.67
    ...
    0.63
    ​
    0.60
    </i>
    0.58
    &#
    0.58
     postIndex
    0.58
    '--
    0.57
    ---
    0.56
    Act Density 0.138%

    No Known Activations