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

    Neuronpedia

    INDEX
    Explanations

    code and configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Firm
    -0.09
    ē
    -0.08
     noun
    -0.08
    (pin
    -0.07
    .dtp
    -0.07
     IBOutlet
    -0.07
     sposób
    -0.07
    ně
    -0.07
    IRQ
    -0.07
    nju
    -0.07
    POSITIVE LOGITS
         ↵
    0.08
     Axe
    0.08
     mane
    0.08
       
↵
    0.08
     Ashley
    0.07
               
↵
    0.07
               ↵
    0.07
    盒
    0.07
     estrutur
    0.07
     exce
    0.07
    Act Density 0.008%

    No Known Activations