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

    Neuronpedia

    INDEX
    Explanations

    themes of sacrifice and protection

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

    taking a blow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.61
    featureID
    -0.59
     cherchés
    -0.53
    紆
    -0.52
    RegressionTest
    -0.52
     PLWABN
    -0.51
    mbic
    -0.51
    Життєпис
    -0.50
     initComponents
    -0.50
    setArguments
    -0.50
    POSITIVE LOGITS
     îns
    0.37
     legais
    0.33
     protecting
    0.32
     sacrifice
    0.31
     poświę
    0.31
     sacrificio
    0.31
     expend
    0.30
     instead
    0.30
    Ephe
    0.30
     protective
    0.29
    Act Density 0.040%

    No Known Activations