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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships in discussions of rights and identity

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

    Text after conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     showcasing
    -0.71
    klart
    -0.69
     niveaux
    -0.69
    Yep
    -0.66
     Importantly
    -0.64
    complexContent
    -0.62
    شون
    -0.62
     Yep
    -0.62
    Yeah
    -0.61
     vectorielles
    -0.61
    POSITIVE LOGITS
     doubtless
    0.72
     such
    0.66
     there
    0.66
     men
    0.65
     thereupon
    0.64
     it
    0.61
     persons
    0.61
     scarcely
    0.60
     hitherto
    0.60
     they
    0.58
    Act Density 0.504%

    No Known Activations