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

    Neuronpedia

    INDEX
    Explanations

    references to expertise and knowledge levels in various contexts

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

    knowledgeable advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unique
    -0.29
     Насе
    -0.28
    patreon
    -0.28
    Wikimedia
    -0.27
     serons
    -0.27
     suy
    -0.26
     kari
    -0.26
     INVESTIG
    -0.26
    Demografía
    -0.26
     irresistible
    -0.26
    POSITIVE LOGITS
    expert
    0.94
     expert
    0.88
     Expert
    0.85
    experts
    0.85
    Expert
    0.84
     experts
    0.82
     Experts
    0.79
    Experts
    0.77
     expertos
    0.75
     experto
    0.74
    Act Density 0.049%

    No Known Activations