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

    Neuronpedia

    INDEX
    Explanations

    phrases of explanation or justification

    oai_token-act-pair · gemini-2.0-flash

    Hedging and describing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.66
     useAppContext
    -0.60
     ↓,
    -0.59
    ftagPool
    -0.56
    URLException
    -0.54
    ukone
    -0.52
    saraba
    -0.52
    ArgsConstructor
    -0.52
    septic
    -0.51
     >=",
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.68
    complexContent
    0.55
     compéti
    0.52
    DockStyle
    0.52
     كورة
    0.51
     controllare
    0.50
    TagHelpers
    0.50
     sélection
    0.50
     siè
    0.50
    mack
    0.49
    Act Density 2.362%

    No Known Activations