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

    Neuronpedia

    INDEX
    Explanations

    references to tragic events and casualties

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

    place names and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     henvisninger
    -0.50
    //
    -0.44
     ProtoMessage
    -0.41
     intStringLen
    -0.40
    adaptiveStyles
    -0.39
     gafas
    -0.37
    gafas
    -0.37
    awtextra
    -0.37
     
    -0.36
    exitRule
    -0.36
    POSITIVE LOGITS
     GenerationType
    0.57
     informée
    0.52
     IRC
    0.50
     Deaths
    0.50
    __;
    0.49
    HomeAsUpEnabled
    0.49
     raid
    0.49
    OSC
    0.48
     stam
    0.47
    Disaster
    0.47
    Act Density 0.024%

    No Known Activations