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

    Neuronpedia

    INDEX
    Explanations

    Code/system messages

    np_max-act · gemini-2.0-flash

    The neuron is activated by the prompt’s section‐separator or heading tokens (e.g. “## Response:”) indicating the start of the assistant’s response section.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tal
    -0.07
     VIII
    -0.07
     status
    -0.07
     opting
    -0.07
     Status
    -0.07
    ={$
    -0.06
     decided
    -0.06
    _dev
    -0.06
     Panic
    -0.06
     Policies
    -0.06
    POSITIVE LOGITS
    AnimationFrame
    0.07
    .surname
    0.06
    encoding
    0.06
    &w
    0.06
     unlawful
    0.06
     Ceramic
    0.06
     truyền
    0.06
     enerj
    0.06
     Deutsche
    0.06
     ejac
    0.06
    Act Density 0.036%

    No Known Activations