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

    Neuronpedia

    INDEX
    Explanations

    learning lessons

    np_max-act · gemini-2.0-flash

    The neuron fires on text about creating or requesting lesson plans (e.g. when “lesson,” “plan,” or teaching‐related instructions appear).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     škol
    -0.07
    (dto
    -0.07
     wand
    -0.07
     anders
    -0.06
     CREATE
    -0.06
     Johann
    -0.06
    -Qaeda
    -0.06
    à
    -0.06
    .Auth
    -0.06
     hä
    -0.06
    POSITIVE LOGITS
    강
    0.07
     обеспеч
    0.07
     herhangi
    0.07
     б
    0.06
    -world
    0.06
     demir
    0.06
    ">&#
    0.06
     supreme
    0.06
    topic
    0.06
     오늘
    0.06
    Act Density 0.036%

    No Known Activations