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

    Neuronpedia

    INDEX
    Explanations

    Mixtures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deploy
    -0.07
     remodel
    -0.07
     UIKit
    -0.07
     restroom
    -0.07
     Desktop
    -0.07
    ит
    -0.07
    Kal
    -0.06
     sergeant
    -0.06
    oku
    -0.06
     sanitize
    -0.06
    POSITIVE LOGITS
    (ident
    0.06
     historia
    0.06
     prepared
    0.06
    طي
    0.06
    属
    0.06
     sourceMapping
    0.06
     subordinate
    0.06
     Oxford
    0.06
    +'&
    0.06
     هد
    0.06
    Act Density 0.039%

    No Known Activations