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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and recognition for achievements

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

    Expressing gratitude or humility

    np_acts-logits-general · gemini-2.0-flash

    feeling good about accomplishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liet
    -0.56
    ponses
    -0.54
    ClientRect
    -0.53
     tsk
    -0.51
     springfox
    -0.51
    lickr
    -0.49
    δρ
    -0.48
    ularity
    -0.47
    charCodeAt
    -0.46
    Composable
    -0.46
    POSITIVE LOGITS
     humbled
    0.87
     humbling
    0.82
     humbly
    0.80
     overjoyed
    0.78
     gratification
    0.75
     gratifying
    0.74
     flattered
    0.74
     proudest
    0.72
     congratulations
    0.70
     elated
    0.69
    Act Density 0.169%

    No Known Activations