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

    Neuronpedia

    INDEX
    Explanations

    javascript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cherish
    -0.07
     mixing
    -0.07
     ate
    -0.06
     danske
    -0.06
     Heat
    -0.06
     Gson
    -0.06
     presume
    -0.06
    (ip
    -0.06
     pancakes
    -0.06
     tracer
    -0.06
    POSITIVE LOGITS
    boxing
    0.07
     Prev
    0.07
    onda
    0.07
     cows
    0.06
     nett
    0.06
    .querySelectorAll
    0.06
    три
    0.06
     впол
    0.06
    entialAction
    0.06
     migliori
    0.06
    Act Density 0.001%

    No Known Activations