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

    Neuronpedia

    INDEX
    Explanations

    references to biases and limitations in research studies

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

    review and summarize studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.53
    featureID
    -0.53
     esternos
    -0.45
    Παραπομπές
    -0.42
     PRES
    -0.42
     ContentValues
    -0.41
     combattre
    -0.41
     devriez
    -0.40
    DoubleQuotes
    -0.40
    GIH
    -0.40
    POSITIVE LOGITS
     summaries
    0.47
     summary
    0.47
     summarizing
    0.44
     обзор
    0.43
    summary
    0.40
     referenties
    0.40
     summar
    0.40
     evaluation
    0.39
    summar
    0.39
     systematic
    0.38
    Act Density 0.201%

    No Known Activations