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

    Neuronpedia

    INDEX
    Explanations

    random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dataset
    -0.08
    Добав
    -0.07
     />
↵
    -0.07
    _PLACE
    -0.07
    تو
    -0.06
     Rails
    -0.06
     mosques
    -0.06
    _marks
    -0.06
     sites
    -0.06
     Emperor
    -0.06
    POSITIVE LOGITS
     imposs
    0.06
     zahl
    0.06
     menn
    0.06
    .cljs
    0.06
     inve
    0.06
     lässt
    0.06
    okino
    0.06
    .until
    0.06
    att
    0.05
     moduleId
    0.05
    Act Density 0.020%

    No Known Activations