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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses

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

    court did

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -1.16
     للمعارف
    -0.87
    RegressionTest
    -0.77
    TintMode
    -0.74
    ьаж
    -0.72
    FailureListener
    -0.69
     referenties
    -0.68
     Meksiku
    -0.68
    RegistryLite
    -0.67
    OGND
    -0.66
    POSITIVE LOGITS
    AlterField
    0.55
     type
    0.53
     model
    0.53
    Glej
    0.50
    model
    0.50
     ось
    0.48
     kind
    0.48
    Model
    0.47
     seres
    0.47
    OLY
    0.47
    Act Density 0.003%

    No Known Activations