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

    Neuronpedia

    INDEX
    Explanations

    code/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiếng
    -0.07
    .idx
    -0.06
     cyan
    -0.06
    margin
    -0.06
    提升
    -0.06
    ="/"
    -0.06
    gregation
    -0.06
     dbName
    -0.06
     arous
    -0.06
     nobody
    -0.06
    POSITIVE LOGITS
    attended
    0.08
    -sur
    0.07
    615
    0.07
    Bu
    0.07
    895
    0.07
    Ce
    0.06
    470
    0.06
     goTo
    0.06
     CRM
    0.06
    Eventually
    0.06
    Act Density 0.000%

    No Known Activations