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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions related to actions

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

    commands and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.33
    urysty
    -0.31
     awakeFromNib
    -0.31
    WritableDatabase
    -0.30
     Badezimmer
    -0.30
     Reisen
    -0.29
    níku
    -0.29
    yski
    -0.28
     Dead
    -0.28
     rail
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.52
    thodoxy
    0.52
    󠁣
    0.51
    Aholisi
    0.51
     Casualty
    0.49
    ロウィン
    0.48
     defaultstate
    0.47
    iſchen
    0.47
     հղումներ
    0.47
     AssemblyProduct
    0.47
    Act Density 0.132%

    No Known Activations