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

    Neuronpedia

    INDEX
    Explanations

    references to devices and operational methods in technology or processes

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

    Kiki will use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.42
    Uris
    -0.37
    ziasztok
    -0.36
    BagLayout
    -0.36
    ukone
    -0.36
     newOwner
    -0.36
     NSError
    -0.36
     reda
    -0.36
     vinto
    -0.36
     contribuer
    -0.35
    POSITIVE LOGITS
     inserting
    0.59
     unplug
    0.58
    把
    0.58
    :✨
    0.57
     placing
    0.57
     swapping
    0.56
    placing
    0.56
     slapping
    0.55
     deleting
    0.54
     spraying
    0.54
    Act Density 0.871%

    No Known Activations