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

    Neuronpedia

    INDEX
    Explanations

    tons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Memory
    -0.07
    Marshal
    -0.07
    علوم
    -0.07
     confession
    -0.07
     рам
    -0.07
     Changing
    -0.07
    Formatted
    -0.06
    .With
    -0.06
     diagnose
    -0.06
     }};↵
    -0.06
    POSITIVE LOGITS
    sur
    0.06
     titre
    0.06
     Мож
    0.06
     نادي
    0.06
     hamburger
    0.06
    ейств
    0.06
     BM
    0.06
     yapılan
    0.06
    >T
    0.06
     deficit
    0.06
    Act Density 0.014%

    No Known Activations