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

    Neuronpedia

    INDEX
    Explanations

    that is mainly from

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

    instructions and meta-discussions about AI models, their capabilities or constraints, especially jailbreak-style prompts and references to policies or system rules.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ⵛ
    0.35
    ┍
    0.34
    يف
    0.33
    胍
    0.33
    ლე
    0.33
    ？](
    0.32
    ␥
    0.32
    ﺔ
    0.32
    άλ
    0.32
    ί
    0.32
    POSITIVE LOGITS
     that
    0.37
     advertisement
    0.36
     providence
    0.35
     Youtube
    0.34
     not
    0.32
     customer
    0.32
     vision
    0.32
     rod
    0.32
     time
    0.31
     It
    0.31
    Act Density 3.103%

    No Known Activations