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

    Neuronpedia

    INDEX
    Explanations

    Unique

    np_max-act · gemini-2.0-flash

    interrogative phrases—tokens that begin or appear in questions (e.g., "What", "Do you", "Have you", question prompts).

    oai_token-act-pair · gpt-5-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    щей
    -0.07
    آمد
    -0.07
     jedna
    -0.07
    uppy
    -0.07
     tie
    -0.06
     Tie
    -0.06
     Governments
    -0.06
     innings
    -0.06
    amba
    -0.06
    .ai
    -0.06
    POSITIVE LOGITS
    갤
    0.07
    ์ว
    0.06
    .fix
    0.06
     pré
    0.06
     utilizando
    0.06
     objetivo
    0.06
    Ver
    0.06
    	Console
    0.06
    MES
    0.06
    Permanent
    0.06
    Act Density 0.065%

    No Known Activations