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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ов
    -0.07
    onda
    -0.06
    alarda
    -0.06
    不过
    -0.06
    _vectors
    -0.06
    .parameter
    -0.06
     MetroFramework
    -0.06
    _notifier
    -0.06
     jenom
    -0.06
     влад
    -0.06
    POSITIVE LOGITS
     aspect
    0.07
     suit
    0.07
     systems
    0.07
    ham
    0.06
     sued
    0.06
    lib
    0.06
    SY
    0.06
     Scene
    0.06
     system
    0.06
     valuable
    0.06
    Act Density 0.009%

    No Known Activations