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

    Neuronpedia

    INDEX
    Explanations

    references to people, organizations, and their roles or actions in a narrative context

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

    applied in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    break
    -0.46
     break
    -0.38
    clear
    -0.37
    oredCriteria
    -0.33
    see
    -0.32
    broken
    -0.32
     Numerade
    -0.31
    buttons
    -0.31
    lighter
    -0.31
    ":[{
    -0.30
    POSITIVE LOGITS
    Xna
    0.51
    ✨:
    0.50
     EconPapers
    0.50
    usermodel
    0.49
     kasarigan
    0.48
    SBATCH
    0.48
    AnchorStyles
    0.47
    новништво
    0.46
    SerializedSize
    0.46
    sonaro
    0.45
    Act Density 0.040%

    No Known Activations