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

    Neuronpedia

    INDEX
    Explanations

    Proposal

    np_max-act · gemini-2.0-flash

    The neuron flags words that name or label the type of document or section (e.g. “plan,” “project,” “contract,” “proposal,” “report,” “strategy document,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Peak
    -0.07
    Messaging
    -0.07
    CEE
    -0.06
     crushing
    -0.06
    .watch
    -0.06
    nodiscard
    -0.06
     furry
    -0.06
    Bruce
    -0.06
    talk
    -0.06
    کنان
    -0.06
    POSITIVE LOGITS
     '',
    0.07
     ''.
    0.07
    users
    0.06
    思想
    0.06
     cedar
    0.06
    Coal
    0.06
     لق
    0.06
    yms
    0.06
     Hemp
    0.06
    ões
    0.06
    Act Density 0.086%

    No Known Activations