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

    Neuronpedia

    INDEX
    Explanations

    negations or phrases indicating doubt or exceptions

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

    Negation or denial

    np_acts-logits-general · gemini-2.0-flash

    not unusual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urlpatterns
    -0.69
    ByPrimaryKey
    -0.64
    parsedMessage
    -0.62
    WebServlet
    -0.59
     يتيمه
    -0.58
    ynb
    -0.57
    MLLoader
    -0.55
    argout
    -0.55
     véritables
    -0.52
     Signalez
    -0.52
    POSITIVE LOGITS
     joke
    0.65
    MockBean
    0.61
    jok
    0.58
     Isolated
    0.56
     joking
    0.55
     isolated
    0.55
     joked
    0.54
    Isolated
    0.54
     jokes
    0.53
     jok
    0.52
    Act Density 0.198%

    No Known Activations