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

    Neuronpedia

    INDEX
    Explanations

    words related to construction and building processes

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

    describing items that were constructed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QueryParam
    -0.59
    GetAxis
    -0.56
     Geſch
    -0.56
     Geiſt
    -0.54
     ſeinen
    -0.54
     ſehen
    -0.54
    Relevant
    -0.53
    Alive
    -0.53
     müſſen
    -0.53
     oczy
    -0.53
    POSITIVE LOGITS
     constructed
    1.37
     construction
    1.26
     Constructed
    1.15
     Construction
    1.13
    Constructed
    1.12
    Construction
    1.07
    constructed
    1.07
    construction
    1.04
     constructing
    1.04
     CONSTRUCTION
    0.96
    Act Density 0.019%

    No Known Activations