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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ĐT
    -0.07
    却是
    -0.07
     EVENTS
    -0.07
    去找
    -0.07
     recieved
    -0.07
     transl
    -0.07
     toe
    -0.07
     после
    -0.07
    鹯
    -0.07
     swapped
    -0.07
    POSITIVE LOGITS
    enda
    0.07
    SDL
    0.07
    apid
    0.07
    unas
    0.07
    ")).
    0.07
    cuda
    0.06
     forests
    0.06
    inde
    0.06
    iga
    0.06
    )){
↵
    0.06
    Act Density 0.010%

    No Known Activations