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

    Neuronpedia

    INDEX
    Explanations

    terms related to the action of deletion

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

    delete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jîn
    -0.72
     iface
    -0.59
    workbench
    -0.59
     CURIAM
    -0.58
    Koordinaten
    -0.56
    verifyException
    -0.55
     للمعارف
    -0.55
    wic
    -0.54
     חיצוניים
    -0.54
     Manner
    -0.54
    POSITIVE LOGITS
     Delete
    1.00
    delete
    0.99
     delete
    0.96
     DELETE
    0.93
    Delete
    0.91
    DELETE
    0.83
    HttpDelete
    0.80
    DeleteMapping
    0.78
     Deletes
    0.73
     deletion
    0.72
    Act Density 0.015%

    No Known Activations