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
    obre
    -0.07
     nob
    -0.07
     trustees
    -0.06
    Separ
    -0.06
    事情
    -0.06
    よりも
    -0.06
    \Routing
    -0.06
    _get
    -0.06
     logs
    -0.06
     boh
    -0.06
    POSITIVE LOGITS
     [[]
    0.06
    로서
    0.06
     CompletableFuture
    0.06
     Elliott
    0.06
     Psychiatry
    0.06
     навер
    0.06
    扱
    0.06
     Desmond
    0.06
     prime
    0.06
    ůr
    0.06
    Act Density 0.001%

    No Known Activations