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

    Neuronpedia

    INDEX
    Explanations

    references to data retrieval functions or methods in code

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

    find by id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.69
    EDEFAULT
    -0.68
    bitField
    -0.67
     lenker
    -0.64
     leaſt
    -0.61
     resourceCulture
    -0.60
    RenderAtEndOf
    -0.59
    UnknownFieldSet
    -0.58
     itſelf
    -0.57
     ſche
    -0.56
    POSITIVE LOGITS
     findById
    0.50
    ById
    0.40
    りを
    0.40
    celana
    0.36
    TERMIN
    0.35
    ispo
    0.35
     getById
    0.35
     нормы
    0.35
    eado
    0.35
     diensten
    0.35
    Act Density 0.005%

    No Known Activations