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

    Neuronpedia

    INDEX
    Explanations

    Past experiences

    np_max-act · gemini-2.0-flash

    instances where the text signals prior occurrence or familiarity (that something or someone has been experienced or seen before).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     país
    -0.07
     حالت
    -0.06
    scenes
    -0.06
    Internal
    -0.06
    NameValuePair
    -0.06
     ниж
    -0.06
    Ik
    -0.06
     вра
    -0.06
     kako
    -0.06
     retrieves
    -0.06
    POSITIVE LOGITS
    voir
    0.07
    .cid
    0.07
     \<^
    0.06
     Hamburg
    0.06
     �
    0.06
    .SpringBootApplication
    0.06
     MainMenu
    0.06
    Memo
    0.06
    Activities
    0.06
    Insensitive
    0.06
    Act Density 0.116%

    No Known Activations