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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    The neuron activates on the assistant’s expressions of willingness or offers to help (e.g. “help you,” “happy to help,” “be happy to assist”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Length
    -0.07
    кра
    -0.07
     Shirley
    -0.07
    .cards
    -0.07
    ció
    -0.07
    /ca
    -0.06
    -stars
    -0.06
    .gf
    -0.06
    _income
    -0.06
    intestinal
    -0.06
    POSITIVE LOGITS
     hasher
    0.07
     JButton
    0.06
    ECT
    0.06
    Anyone
    0.06
    alloween
    0.06
     Mud
    0.06
    іть
    0.06
     hearts
    0.06
     Halloween
    0.06
    础
    0.06
    Act Density 0.025%

    No Known Activations