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

    Neuronpedia

    INDEX
    Explanations

    names and references to specific individuals or companies

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

    personal statements and vulnerable people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COVID
    -0.45
    COVID
    -0.42
     covid
    -0.42
    SharedCtor
    -0.42
     https
    -0.41
    ️⃣
    -0.41
     continúas
    -0.39
     ✅
    -0.39
    covid
    -0.38
     ChatGPT
    -0.38
    POSITIVE LOGITS
     desmotivaciones
    0.54
     kasarigan
    0.50
     ſont
    0.48
     increí
    0.47
     femeninos
    0.46
     motivadoras
    0.46
     ainfi
    0.46
     étoient
    0.44
    stoß
    0.42
    jden
    0.42
    Act Density 0.381%

    No Known Activations