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
    xfe
    -0.07
     barracks
    -0.07
     restart
    -0.07
     Coca
    -0.06
    ová
    -0.06
     αποτε
    -0.06
     professions
    -0.06
     laten
    -0.06
     predecessor
    -0.06
     prerequisites
    -0.06
    POSITIVE LOGITS
    нив
    0.07
     by
    0.07
    Access
    0.06
    ủa
    0.06
    /dr
    0.06
    υ
    0.06
     يح
    0.06
     Comparator
    0.06
    ẫn
    0.06
     différent
    0.06
    Act Density 0.042%

    No Known Activations