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

    Neuronpedia

    INDEX
    Explanations

    words related to exploration and discovery

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

    "Discover" or "explore" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    explore and discover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    -0.64
    genstein
    -0.64
      
    -0.61
     отношению
    -0.58
    所
    -0.57
    weise
    -0.55
     douane
    -0.54
    日在
    -0.54
    ally
    -0.54
    espan
    -0.53
    POSITIVE LOGITS
    ."</
    0.80
    })));
    0.77
     Discover
    0.77
    TestingModule
    0.72
     discovery
    0.72
     découvrir
    0.71
    DISCOVER
    0.71
    OuterClass
    0.71
    ">//
    0.71
    !<
    0.70
    Act Density 0.135%

    No Known Activations