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

    Neuronpedia

    INDEX
    Explanations

    references to assistance or support for others

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

    helping others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.60
     spreken
    -0.46
     punctu
    -0.43
    matchCondition
    -0.42
     Chwiliwch
    -0.40
     елның
    -0.38
     punctuated
    -0.38
    VIAF
    -0.38
     '\\;'
    -0.36
     ActivatedRoute
    -0.36
    POSITIVE LOGITS
     Helping
    0.62
    Helping
    0.60
    helping
    0.59
    help
    0.53
    TagMode
    0.52
     Help
    0.50
     HELP
    0.48
    Help
    0.48
    HELP
    0.47
     Helpers
    0.46
    Act Density 0.022%

    No Known Activations