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

    Neuronpedia

    INDEX
    Explanations

    failed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (type
    -0.06
    čen
    -0.06
     notify
    -0.06
    agnitude
    -0.06
    ibs
    -0.06
    ullivan
    -0.06
     Ад
    -0.06
    TimeZone
    -0.06
    mek
    -0.06
    okes
    -0.06
    POSITIVE LOGITS
     Fahr
    0.07
    emouth
    0.07
    .robot
    0.06
     deleteUser
    0.06
    ーツ
    0.06
     czy
    0.06
     Fashion
    0.06
     rover
    0.06
     startActivity
    0.06
    .PostMapping
    0.06
    Act Density 0.004%

    No Known Activations