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

    Neuronpedia

    INDEX
    Explanations

    helper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rock
    -0.07
     Đầu
    -0.07
    /values
    -0.06
    Church
    -0.06
    영
    -0.06
    BF
    -0.06
     falls
    -0.06
     McN
    -0.06
     Polynomial
    -0.06
     polarization
    -0.06
    POSITIVE LOGITS
     helper
    0.07
     cute
    0.07
    .await
    0.07
     aspir
    0.06
    .city
    0.06
     anymore
    0.06
    SharedPreferences
    0.06
     (*(
    0.06
    krvldkf
    0.06
    _ment
    0.06
    Act Density 0.001%

    No Known Activations