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

    Neuronpedia

    INDEX
    Explanations

    words that suggest causes and effects, and strong opinions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DebuggerStep
    -0.44
     Ordin
    -0.38
    let
    -0.38
    ough
    -0.38
    bol
    -0.37
    och
    -0.37
    eve
    -0.36
     nul
    -0.35
     Jules
    -0.35
    lets
    -0.35
    POSITIVE LOGITS
    InjectAttribute
    0.89
    MemoryWarning
    0.82
    CloseOperation
    0.78
     للاسماء
    0.75
     BoxDecoration
    0.75
     चीज़ों
    0.75
    __":
    0.71
     дописавши
    0.71
    contentLoaded
    0.69
    SaveChangesAsync
    0.67
    Act Density 0.851%

    No Known Activations