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

    Neuronpedia

    INDEX
    Explanations

    words related to construction and deconstruction processes

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

    deconvolution, decoupled, decompression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.54
     समीक्षाओं
    -0.52
    Cyfarwyddwr
    -0.45
    市镇
    -0.45
     gyhoeddwyd
    -0.44
     خارجية
    -0.43
     saites
    -0.43
    Means
    -0.43
    LookAnd
    -0.42
     Means
    -0.42
    POSITIVE LOGITS
     decon
    0.75
     decontamination
    0.60
     decou
    0.59
     unstructured
    0.50
     Eck
    0.50
     deco
    0.48
     Dek
    0.48
     decentralized
    0.47
    デコ
    0.47
     dec
    0.47
    Act Density 0.012%

    No Known Activations