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

    Neuronpedia

    INDEX
    Explanations

    definitions and formal descriptions from authoritative sources

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retriever
    -0.35
    EDEFAULT
    -0.32
    JsonProperty
    -0.31
     kuda
    -0.31
    …~
    -0.30
     κατά
    -0.29
     createSlice
    -0.28
     store
    -0.27
    ayne
    -0.27
     Retriever
    -0.27
    POSITIVE LOGITS
     autorytatywna
    0.62
     Autorisations
    0.59
    awtextra
    0.56
    الحياه
    0.54
     EconPapers
    0.51
    GraphicsUnit
    0.50
     Signalez
    0.50
    Vidite
    0.49
    agisse
    0.49
    ppelin
    0.47
    Act Density 0.116%

    No Known Activations