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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Categorie
    -0.08
     foy
    -0.08
     jus
    -0.08
    ployed
    -0.08
     مرسته
    -0.08
     istifadə
    -0.07
    locker
    -0.07
    Counters
    -0.07
     leisurely
    -0.07
    SORT
    -0.07
    POSITIVE LOGITS
     disag
    0.08
     comparing
    0.08
     agreement
    0.08
     দ্ব
    0.08
     breakpoint
    0.07
     contradiction
    0.07
     exchanging
    0.07
     implying
    0.07
     equation
    0.07
     compare
    0.07
    Act Density 0.091%

    No Known Activations