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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace or spacing between words

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

    legal case citations like `v.`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ésultats
    -0.84
    Personendaten
    -0.82
     desmotivaciones
    -0.81
    ágenes
    -0.80
     increí
    -0.80
     queſta
    -0.77
    linawan
    -0.75
    ſelf
    -0.73
     ſche
    -0.73
    ientras
    -0.72
    POSITIVE LOGITS
     
    0.66
    1
    0.47
     (
    0.46
    ↵↵
    0.43
     +
    0.43
     /
    0.43
     Hu
    0.43
     $
    0.43
     \
    0.42
    <td>
    0.42
    Act Density 0.015%

    No Known Activations