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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convergence
    -0.07
    -handler
    -0.07
    ()},
    -0.07
    �
    -0.07
    歩
    -0.06
    康
    -0.06
    اءات
    -0.06
    .Servlet
    -0.06
    etable
    -0.06
    wner
    -0.06
    POSITIVE LOGITS
     oblivious
    0.07
    leyici
    0.06
    verture
    0.06
    ully
    0.06
     unclear
    0.06
    ienda
    0.06
    quared
    0.06
    rosso
    0.06
    txt
    0.06
    WM
    0.06
    Act Density 0.006%

    No Known Activations