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

    Neuronpedia

    INDEX
    Explanations

    patterns of repetition or significant sequences in data

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    coding and extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.63
    ագրություններ
    -0.57
    Rhestr
    -0.57
     continúas
    -0.56
    InitVars
    -0.54
    álat
    -0.54
    AsUp
    -0.54
    tanleria
    -0.53
     assoluto
    -0.51
    ask
    -0.51
    POSITIVE LOGITS
    </thead>
    0.65
    }")
    0.65
    ">:
    0.62
    matician
    0.62
    '])
    0.60
    IBOutlet
    0.59
    /');
    0.59
    """.
    0.56
    typeorm
    0.56
    AddTagHelper
    0.55
    Act Density 0.244%

    No Known Activations