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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Names
    -0.07
    hospital
    -0.07
    ent
    -0.06
     getModel
    -0.06
     lesions
    -0.06
     conductivity
    -0.06
    persistent
    -0.06
     dbc
    -0.06
    -factor
    -0.06
    pNet
    -0.06
    POSITIVE LOGITS
    .NonNull
    0.07
     fracking
    0.06
     مد
    0.06
    XX
    0.06
     ATV
    0.06
     뉴
    0.06
     прик
    0.06
    pga
    0.06
    ！」↵↵
    0.06
    utzt
    0.06
    Act Density 0.003%

    No Known Activations