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

    Neuronpedia

    INDEX
    Explanations

    words related to exploration and examination of topics or subjects

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

    examine and explore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.60
    Tikang
    -0.59
     estekak
    -0.52
    oneofs
    -0.52
    contentLoaded
    -0.50
    SOUNDBITE
    -0.50
    migrationBuilder
    -0.50
    makeText
    -0.50
    govina
    -0.49
     ffilmiau
    -0.49
    POSITIVE LOGITS
     examines
    0.77
     examine
    0.75
     explored
    0.73
     examined
    0.71
     examining
    0.70
     explores
    0.68
     explore
    0.67
    examined
    0.64
    Exploring
    0.61
     exploring
    0.61
    Act Density 0.147%

    No Known Activations