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

    Neuronpedia

    INDEX
    Explanations

    names of people and references to individuals in a historical or literary context

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

    names and inventors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.64
    -0.60
    featureID
    -0.56
     Truths
    -0.54
     otomatig
    -0.53
     upcoming
    -0.53
     snippetHide
    -0.52
    oa̍t
    -0.50
     autorytatywna
    -0.50
     truths
    -0.50
    POSITIVE LOGITS
     murieron
    0.41
     fondateur
    0.35
    expectedResult
    0.34
     meubles
    0.33
     muerto
    0.33
    ListItemIcon
    0.31
    BagConstraints
    0.31
    databind
    0.30
    ↻
    0.30
     esclavos
    0.30
    Act Density 0.107%

    No Known Activations