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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash

    This neuron activates on words related to personalized or targeted marketing (e.g., personal/personalization, personalized, targeted, targeting, segmentation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    daemon
    -0.07
    rint
    -0.06
    -pro
    -0.06
     WAN
    -0.06
    lements
    -0.06
    .hl
    -0.06
    典
    -0.06
     near
    -0.06
     wake
    -0.06
     b
    -0.06
    POSITIVE LOGITS
    삼
    0.07
     luxurious
    0.07
     швид
    0.06
     aldığı
    0.06
    .stats
    0.06
    感
    0.06
     ศ
    0.06
     đúng
    0.06
    187
    0.06
    씩
    0.06
    Act Density 0.031%

    No Known Activations