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

    Neuronpedia

    INDEX
    Explanations

    recommendations

    np_max-act · gemini-2.0-flash

    the neuron flags calls-to-action (imperative prompts encouraging the reader to share, follow, link up, donate, or otherwise engage).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    shield
    -0.07
     क
    -0.07
    .ship
    -0.07
     wf
    -0.06
     serta
    -0.06
     Sms
    -0.06
    896
    -0.06
    ětš
    -0.06
    _generic
    -0.06
     subdiv
    -0.06
    POSITIVE LOGITS
     söyledi
    0.06
    》，
    0.06
    nilai
    0.06
    惊
    0.06
    (月
    0.06
    、本
    0.06
     hentai
    0.06
    (stat
    0.06
     followers
    0.06
    (日
    0.06
    Act Density 0.011%

    No Known Activations