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
    àng
    -0.08
    愫
    -0.07
    فل
    -0.07
     içerisinde
    -0.07
     bande
    -0.07
    세
    -0.07
     מס
    -0.07
    Bond
    -0.07
    珉
    -0.07
     görm
    -0.07
    POSITIVE LOGITS
    (start
    0.07
    eah
    0.07
     각
    0.07
    槌
    0.07
    =*/
    0.07
    _urls
    0.07
    一架
    0.07
     cruis
    0.07
    *v
    0.07
     /↵↵
    0.07
    Act Density 0.002%

    No Known Activations