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

    Neuronpedia

    INDEX
    Explanations

    language associated with marketing and guarantees

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.67
    DoubleQuotes
    -0.66
     виправивши
    -0.61
    MessageOf
    -0.61
    InjectAttribute
    -0.54
    MessageTagHelper
    -0.52
    bey
    -0.51
    цездатний
    -0.49
    こと
    -0.49
    èbres
    -0.47
    POSITIVE LOGITS
     estekak
    0.64
     endwhile
    0.59
    MemoryWarning
    0.58
    Πηγή
    0.56
     kasarigan
    0.56
    wieś
    0.54
     kuin
    0.53
    جستارهای
    0.52
    thargy
    0.51
    ⤒
    0.51
    Act Density 1.048%

    No Known Activations