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

    Neuronpedia

    INDEX
    Explanations

    reasoning and thinking abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    name
    0.62
    value
    0.59
    service
    0.57
    not
    0.56
    plist
    0.56
    data
    0.55
    klass
    0.55
    catalog
    0.54
    phenylsulfanyl
    0.54
    time
    0.53
    POSITIVE LOGITS
     intellect
    0.80
    🧠
    0.75
     reasoning
    0.74
     brain
    0.73
     cognitive
    0.72
     Reasoning
    0.72
     cognitiva
    0.72
     cerveau
    0.70
     Cognitive
    0.68
     cognition
    0.62
    Act Density 0.138%

    No Known Activations