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

    Neuronpedia

    INDEX
    Explanations

    references to containers and their uses

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

    associated with containers

    np_acts-logits-general · gemini-2.0-flash

    containers and their contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gaben
    -0.54
    ulink
    -0.51
    jane
    -0.51
     palvel
    -0.49
     biały
    -0.49
     للمعارف
    -0.48
     cardiaque
    -0.48
     richesse
    -0.48
     ringan
    -0.48
    året
    -0.47
    POSITIVE LOGITS
     lid
    0.91
     lids
    0.86
    ful
    0.85
     contents
    0.84
    fuls
    0.80
    findpost
    0.74
     emptying
    0.72
     filled
    0.70
    filling
    0.69
     liner
    0.68
    Act Density 0.256%

    No Known Activations