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

    Neuronpedia

    INDEX
    Explanations

    expressions of nostalgia and emotional intensity

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

    states of being, fire, light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.88
    zzleHttp
    -0.75
    setVerticalGroup
    -0.63
     Administrativna
    -0.61
    ScopeManager
    -0.61
    期刊论文
    -0.61
     EconPapers
    -0.61
     queſta
    -0.60
    +#+#
    -0.59
     createState
    -0.58
    POSITIVE LOGITS
     spark
    0.57
     among
    0.45
     light
    0.44
    spark
    0.42
     flame
    0.42
     burning
    0.40
     shining
    0.39
     embers
    0.39
     seed
    0.39
     fire
    0.38
    Act Density 0.051%

    No Known Activations