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

    Neuronpedia

    INDEX
    Explanations

    write me a

    np_acts-logits-general · gemini-2.5-flash-lite

    explicit user instructions to generate content, especially imperative prompts that specify a format or deliverable.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    \},
    0.38
    centerX
    0.35
    indexBuffer
    0.35
    applic
    0.35
    spicuous
    0.34
     betroffen
    0.34
     addirittura
    0.33
    exists
    0.33
     zelfs
    0.33
    infrastructure
    0.33
    POSITIVE LOGITS
     poem
    0.61
     poems
    0.57
     screenplay
    0.55
     songwriting
    0.55
     chatbot
    0.54
     photoshoot
    0.51
     wedding
    0.50
     comedy
    0.50
     노래
    0.49
     shayari
    0.49
    Act Density 0.183%

    No Known Activations