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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the phrase “the following” (as in “Which of the following…”) in question prompts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bose
    -0.07
    dispatcher
    -0.06
     Jal
    -0.06
     Como
    -0.06
    _con
    -0.06
    Wer
    -0.06
    荣
    -0.06
    (formData
    -0.06
     repeats
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     바라
    0.07
    bringing
    0.06
     ViewGroup
    0.06
     fortress
    0.06
     reading
    0.06
    -directory
    0.06
    하우
    0.06
     sentencing
    0.06
     청
    0.06
     disappearing
    0.06
    Act Density 0.005%

    No Known Activations