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

    Neuronpedia

    INDEX
    Explanations

    references to unknown fields in data structures or protocol messages

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

    unknownFields, respiration, koh, Bayer, seawater

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cfm
    -0.43
     Rober
    -0.43
     noDo
    -0.41
    ョ
    -0.40
    Typed
    -0.40
     resourceCulture
    -0.39
    る
    -0.39
     Barrett
    -0.39
    Gener
    -0.38
    LO
    -0.38
    POSITIVE LOGITS
     Koh
    0.92
    Koh
    0.83
    todoList
    0.67
     koh
    0.62
     dopamine
    0.61
     zelve
    0.61
    Inicio
    0.59
     vigilancia
    0.57
     Devi
    0.55
     unknownFields
    0.55
    Act Density 0.009%

    No Known Activations