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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reliability and effectiveness in solutions and measurements

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

    reliable or good estimation/measure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tonsoft
    -0.58
    Hentet
    -0.57
     propOrder
    -0.55
    ItemBackground
    -0.54
    AddTagHelper
    -0.52
     الرياضيه
    -0.52
    Rüyada
    -0.51
    DockStyle
    -0.49
    хьтан
    -0.46
    MLLoader
    -0.46
    POSITIVE LOGITS
    obach
    0.41
     république
    0.39
     aproximado
    0.39
     sache
    0.38
     frites
    0.38
     HttpHeaders
    0.37
     sebaiknya
    0.37
    Neb
    0.37
     poca
    0.36
     commenter
    0.36
    Act Density 0.328%

    No Known Activations