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

    Neuronpedia

    INDEX
    Explanations

    Technical figures/charts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     диви
    -0.07
     getKey
    -0.06
    ительства
    -0.06
    AZY
    -0.06
     уник
    -0.06
     AndAlso
    -0.06
     buckets
    -0.06
    ète
    -0.06
    olulu
    -0.06
     adidas
    -0.06
    POSITIVE LOGITS
     hormones
    0.08
     MÜ
    0.06
    LOUD
    0.06
    .cpp
    0.06
    988
    0.06
     Corbyn
    0.06
     Luft
    0.06
    ист
    0.06
     merge
    0.06
     administrator
    0.06
    Act Density 0.009%

    No Known Activations