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

    Neuronpedia

    INDEX
    Explanations

    Reviews and comments

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot mentions of “review” (and its variants like “reviews,” “reviewer,” etc.), i.e. tokens relating to customer or online reviews.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .task
    -0.07
    .BorderFactory
    -0.06
    最
    -0.06
    uir
    -0.06
     seizures
    -0.06
     struk
    -0.06
    Rew
    -0.06
     اي
    -0.06
    inary
    -0.06
    求
    -0.06
    POSITIVE LOGITS
    .slides
    0.07
    Football
    0.07
    VRTX
    0.07
    ........................
    0.06
    يش
    0.06
    	side
    0.06
     clk
    0.06
    *time
    0.06
    getValue
    0.06
     clit
    0.06
    Act Density 0.011%

    No Known Activations