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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rak
    -0.07
    μά
    -0.06
    Bubble
    -0.06
     perm
    -0.06
    jo
    -0.06
     Classic
    -0.06
     placebo
    -0.06
     enf
    -0.06
     carriage
    -0.06
    scala
    -0.06
    POSITIVE LOGITS
     Logout
    0.07
    .url
    0.07
    еры
    0.07
    /column
    0.07
    ，您
    0.07
    _part
    0.06
     Review
    0.06
     imu
    0.06
     handleMessage
    0.06
    .ExecuteNonQuery
    0.06
    Act Density 0.011%

    No Known Activations