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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash

    This neuron activates on section‐heading cues—especially the token “Information” (and nearby small function words like “for,” “about,” “all”) that mark the start of an informational block.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .savefig
    -0.07
    ｧ
    -0.06
    在线视频
    -0.06
     교수
    -0.06
     Lenovo
    -0.06
     controls
    -0.06
    extracomment
    -0.06
     قابلیت
    -0.06
     cognitive
    -0.06
    cilik
    -0.06
    POSITIVE LOGITS
     Information
    0.09
    Information
    0.07
     Info
    0.07
     information
    0.07
     INFORMATION
    0.07
     информ
    0.07
     info
    0.07
     brochure
    0.06
     muž
    0.06
    ILog
    0.06
    Act Density 0.019%

    No Known Activations