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

    Neuronpedia

    INDEX
    Explanations

    references to competitions and challenges

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

    before tasks, assignments, choices, or votes

    np_acts-logits-general · gemini-2.0-flash

    assigned tasks and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    czegó
    -0.67
     venons
    -0.66
     Meksiku
    -0.66
    IUrlHelper
    -0.65
    IntoConstraints
    -0.63
     للمعارف
    -0.62
    Trotz
    -0.62
    verwijspagina
    -0.61
    easily
    -0.60
    RenderAtEndOf
    -0.60
    POSITIVE LOGITS
     randomly
    0.83
     each
    0.79
     challenge
    0.71
     assigned
    0.70
     teams
    0.66
     tasked
    0.66
     random
    0.66
     participants
    0.66
     Each
    0.65
    random
    0.63
    Act Density 0.334%

    No Known Activations