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

    Neuronpedia

    INDEX
    Explanations

    elements related to changes and improvements in systems or processes

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

    improved or changed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
     EconPapers
    -0.52
     doInBackground
    -0.47
     <<<<<<<<<<<<<<
    -0.46
     незавершена
    -0.45
    jooq
    -0.45
    fjspx
    -0.41
    pfe
    -0.40
    Herm
    -0.40
    unk
    -0.40
    POSITIVE LOGITS
     newOwner
    0.60
     verbess
    0.57
     improved
    0.53
     improvement
    0.53
     changed
    0.52
    improved
    0.52
     changé
    0.50
     zmiany
    0.49
     cambiando
    0.49
     amélior
    0.49
    Act Density 0.573%

    No Known Activations