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

    Neuronpedia

    INDEX
    Explanations

    references to various "worlds" or domains of interest within different contexts

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

    world of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.69
    upuncture
    -0.59
    atalytic
    -0.51
     fotografico
    -0.49
    toise
    -0.48
     comerciais
    -0.47
    nagel
    -0.46
     Constitucional
    -0.46
     kanker
    -0.46
    杷
    -0.45
    POSITIVE LOGITS
    world
    0.79
     mondo
    0.76
     world
    0.76
     mundo
    0.69
     WORLD
    0.64
     worlds
    0.62
    World
    0.62
    worlds
    0.61
     wereld
    0.60
     realm
    0.59
    Act Density 0.016%

    No Known Activations