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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    олош
    -0.06
    ْه
    -0.06
    ορ
    -0.06
     />";↵
    -0.06
    ...)↵↵
    -0.05
    ...'↵
    -0.05
    ارا
    -0.05
     Lists
    -0.05
    努
    -0.05
    .locations
    -0.05
    POSITIVE LOGITS
    384
    0.07
     drawings
    0.07
     entreprise
    0.07
    agg
    0.07
    Russia
    0.07
     Goodman
    0.07
    vester
    0.06
    ,J
    0.06
     onClick
    0.06
    lington
    0.06
    Act Density 0.000%

    No Known Activations