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

    Neuronpedia

    INDEX
    Explanations

    code or web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aturity
    -0.07
     DV
    -0.06
    TT
    -0.06
    Football
    -0.06
    انه
    -0.06
    �
    -0.06
    	rs
    -0.06
    ortality
    -0.06
     inversion
    -0.06
    manda
    -0.06
    POSITIVE LOGITS
    attack
    0.07
     grabbed
    0.07
    Curr
    0.06
     그의
    0.06
     така
    0.06
     atroc
    0.06
     UITableViewController
    0.06
    ための
    0.06
     εμφ
    0.06
     متحده
    0.06
    Act Density 0.495%

    No Known Activations