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

    Neuronpedia

    INDEX
    Explanations

    forum/blog posts

    np_max-act · gemini-2.0-flash

    The neuron fires on user requests about remembering, recalling, or quoting prior messages in the conversation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     consecutive
    -0.07
    cov
    -0.07
    atik
    -0.06
     lần
    -0.06
    chor
    -0.06
    िजन
    -0.06
     dressed
    -0.06
    ότε
    -0.06
     либо
    -0.06
    ума
    -0.06
    POSITIVE LOGITS
    Dod
    0.07
     ει
    0.07
    /pub
    0.06
     Farmers
    0.06
    主义
    0.06
     простран
    0.06
     Projectile
    0.06
    .boolean
    0.06
    235
    0.06
     여러분
    0.06
    Act Density 0.008%

    No Known Activations