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

    Neuronpedia

    INDEX
    Explanations

    trying out new things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Feld
    -0.06
    opez
    -0.06
    Increased
    -0.06
    إن
    -0.06
     Ply
    -0.06
    olas
    -0.06
     Disaster
    -0.06
    ين
    -0.06
    лоб
    -0.06
    Exit
    -0.06
    POSITIVE LOGITS
     своего
    0.07
     frm
    0.06
    ページ
    0.06
    들을
    0.06
    .Private
    0.06
            ↵        ↵        ↵
    0.06
    しい
    0.06
     Answer
    0.06
     tok
    0.06
    @Test
    0.06
    Act Density 0.271%

    No Known Activations