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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or critiques

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

    user context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.70
     >=",
    -0.58
    Gön
    -0.58
    httphttps
    -0.56
     AssemblyCompany
    -0.54
     MainAxisSize
    -0.52
    ſammen
    -0.51
    featureID
    -0.50
    DotNetBar
    -0.50
    MessageTagHelper
    -0.50
    POSITIVE LOGITS
    ={({
    0.38
     Consultado
    0.33
     tarik
    0.33
    KommentareTeilen
    0.32
    ようです
    0.31
    のでしょうか
    0.31
    Jegyzetek
    0.31
    Eth
    0.30
     sih
    0.29
     nonatomic
    0.29
    Act Density 0.166%

    No Known Activations