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

    Neuronpedia

    INDEX
    Explanations

    expressions of gladness or happiness

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

    glad followed by a reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userDetails
    -0.49
     Waterman
    -0.49
    atalos
    -0.47
    <0xD4>
    -0.47
     Waterhouse
    -0.46
    ibm
    -0.46
     Petrus
    -0.42
     behaviours
    -0.42
     Pedersen
    -0.42
     Peters
    -0.41
    POSITIVE LOGITS
    glad
    0.95
    Glad
    0.90
     Glad
    0.88
     GLAD
    0.87
     glad
    0.81
    tagHelperRunner
    0.66
    Willing
    0.63
     gladness
    0.62
    willing
    0.62
    WaitGroup
    0.60
    Act Density 0.002%

    No Known Activations