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

    Neuronpedia

    INDEX
    Explanations

    references to help and support resources

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

    Links to resources or instructions

    np_acts-logits-general · gemini-2.0-flash

    links and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.89
    setVerticalGroup
    -0.85
    awtextra
    -0.82
    PerformLayout
    -0.79
    RegressionTest
    -0.79
    apimachinery
    -0.78
    bootstrapcdn
    -0.75
    IndentedString
    -0.75
    ConstraintMaker
    -0.74
    TestingModule
    -0.71
    POSITIVE LOGITS
     links
    1.18
     resources
    1.03
     tips
    0.98
     link
    0.93
     helpful
    0.92
     Links
    0.92
     useful
    0.89
    Resources
    0.89
    Links
    0.86
     information
    0.85
    Act Density 0.270%

    No Known Activations