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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Properties
    -0.07
     koş
    -0.06
     등록
    -0.06
    ệnh
    -0.06
    payload
    -0.06
    _driver
    -0.06
     accesses
    -0.06
    Forever
    -0.06
     designing
    -0.06
    usiness
    -0.06
    POSITIVE LOGITS
    (["
    0.07
    貼
    0.07
     caste
    0.06
     traveler
    0.06
    rxjs
    0.06
     Lip
    0.06
    DataGridViewTextBoxColumn
    0.06
    uous
    0.06
    (['
    0.06
     alignment
    0.06
    Act Density 0.159%

    No Known Activations