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

    Neuronpedia

    INDEX
    Explanations

    Cron jobs/scheduling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Succ
    -0.08
    ounc
    -0.07
     nobody
    -0.07
    槲
    -0.07
    iets
    -0.07
    оп
    -0.07
    .Cluster
    -0.07
    喏
    -0.07
    ôt
    -0.07
    孰
    -0.07
    POSITIVE LOGITS
     problème
    0.07
    改编
    0.07
     persön
    0.07
     *>
    0.07
     equipos
    0.07
    뛸
    0.07
    }')↵↵
    0.06
     proceso
    0.06
     função
    0.06
    gorith
    0.06
    Act Density 0.006%

    No Known Activations