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

    Neuronpedia

    INDEX
    Explanations

    Learning information/reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .logo
    -0.08
    ково
    -0.07
    \Dependency
    -0.06
     Bien
    -0.06
    264
    -0.06
     belonging
    -0.06
    uilt
    -0.06
    DataManager
    -0.06
     stars
    -0.06
     NSS
    -0.06
    POSITIVE LOGITS
     января
    0.06
     структу
    0.06
     کنیم
    0.06
    fname
    0.06
    )::
    0.06
    -desktop
    0.06
    ushort
    0.06
      ↵↵
    0.06
    Regression
    0.06
    จำก
    0.05
    Act Density 0.122%

    No Known Activations