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

    Neuronpedia

    INDEX
    Explanations

    references to cultural elements and their meanings

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

    "references" or its variants

    np_acts-logits-general · gemini-2.0-flash

    references and allusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.72
    __":
    -0.62
    columnHeader
    -0.56
    clable
    -0.56
     témoignages
    -0.51
     zeichnet
    -0.50
     tasche
    -0.50
    $_.
    -0.50
    viewDidLoad
    -0.48
    Itoa
    -0.48
    POSITIVE LOGITS
     references
    1.06
     allusions
    1.02
     reference
    1.01
     referencing
    0.93
    reference
    0.88
    references
    0.85
     allusion
    0.85
    Reference
    0.83
     References
    0.81
     Reference
    0.79
    Act Density 0.378%

    No Known Activations