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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    The neuron spotlights mentions of the model’s training data (and related training contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     patrol
    -0.07
     Terrain
    -0.06
    //****************************************************************
    -0.06
     era
    -0.06
     teen
    -0.06
    Justin
    -0.06
     OnDestroy
    -0.06
    -other
    -0.06
     autopsy
    -0.06
     Met
    -0.06
    POSITIVE LOGITS
     cess
    0.07
     CRM
    0.07
    acji
    0.07
     vacc
    0.06
     calm
    0.06
    (glm
    0.06
     catches
    0.06
    ,void
    0.06
     *)
    0.06
    daq
    0.06
    Act Density 0.012%

    No Known Activations