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

    Neuronpedia

    INDEX
    Explanations

    Code/webpage text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -help
    -0.06
    ({})↵
    -0.06
     tod
    -0.06
     хотя
    -0.06
     dose
    -0.06
    .Il
    -0.06
    ("{}
    -0.06
     六
    -0.06
     MDB
    -0.06
    xDA
    -0.06
    POSITIVE LOGITS
     swiftly
    0.07
    Segments
    0.07
    ाइन
    0.07
     >=
    0.06
    owns
    0.06
    lum
    0.06
    рол
    0.06
     ppm
    0.06
    (iter
    0.06
    ινη
    0.06
    Act Density 0.000%

    No Known Activations