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

    Neuronpedia

    INDEX
    Explanations

    tools and hardware-related terminology

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

    screws and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.50
    join
    -0.47
    onAttach
    -0.47
     Matos
    -0.46
     join
    -0.46
    layah
    -0.45
    Slf
    -0.45
     list
    -0.45
    ilaian
    -0.44
     зам
    -0.43
    POSITIVE LOGITS
     screwdriver
    1.77
    wdriver
    1.31
     Scre
    0.91
     scre
    0.82
    scre
    0.76
     pliers
    0.71
    Scre
    0.71
    ſchen
    0.60
     tweezers
    0.60
     myſelf
    0.59
    Act Density 0.010%

    No Known Activations