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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical issues and functionality failures

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

    does not work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.53
     ſta
    -0.52
     ſel
    -0.49
     diſt
    -0.48
     pleaſure
    -0.48
     faſt
    -0.47
     leſs
    -0.47
     ſte
    -0.47
     ſur
    -0.46
     Chwiliwch
    -0.45
    POSITIVE LOGITS
     myö
    0.39
     <>",
    0.37
    เคร
    0.37
     cumplido
    0.37
    ErrorListener
    0.37
     unz
    0.37
     Kerja
    0.36
     propOrder
    0.36
    contentLoaded
    0.36
     hulp
    0.36
    Act Density 0.054%

    No Known Activations