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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance or significance

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

    "important"

    np_acts-logits-general · gemini-2.0-flash

    importance and significance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.88
    Дереккөздер
    -0.79
    contentLoaded
    -0.78
     Bourgoin
    -0.74
    ecap
    -0.74
    Autoritní
    -0.71
     MotionEvent
    -0.71
    StructEnd
    -0.71
    webElementXpaths
    -0.71
     Reverso
    -0.70
    POSITIVE LOGITS
     role
    0.76
     importance
    0.72
    importance
    0.71
     Importance
    0.69
     key
    0.68
     penting
    0.65
     Important
    0.64
    Important
    0.63
     aspects
    0.63
     roles
    0.62
    Act Density 0.120%

    No Known Activations