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

    Neuronpedia

    INDEX
    Explanations

    sections of text with no activated content, indicating a lack of meaningful information

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

    Code, math, or seemingly non-English text

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -1.18
     kasarigan
    -0.99
     betweenstory
    -0.95
     Roskov
    -0.92
    OGND
    -0.90
    ArrowToggle
    -0.88
    ########.
    -0.85
    Portale
    -0.83
     Baillargeon
    -0.83
     tartalomajánló
    -0.82
    POSITIVE LOGITS
     д
    0.53
    printStackTrace
    0.46
    ETHING
    0.42
    ÍT
    0.42
     d
    0.41
    mpa
    0.41
    IMPORTED
    0.41
    нку
    0.41
    INER
    0.40
    lysses
    0.39
    Act Density 0.073%

    No Known Activations