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

    Neuronpedia

    INDEX
    Explanations

    titles/honorifics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不同
    -0.07
     ilişkin
    -0.07
     descent
    -0.07
     інші
    -0.07
     Bell
    -0.06
    Content
    -0.06
    lightbox
    -0.06
     deny
    -0.06
    ids
    -0.06
    젝트
    -0.06
    POSITIVE LOGITS
    .reload
    0.06
    kově
    0.06
    -Compatible
    0.06
    elly
    0.06
     Sears
    0.06
    (enc
    0.06
     beforehand
    0.06
    .gb
    0.06
     ESA
    0.06
    黎
    0.06
    Act Density 0.084%

    No Known Activations