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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rapide
    -0.08
    cheon
    -0.07
    .Compose
    -0.07
     uçak
    -0.07
    ”;
    -0.06
    пис
    -0.06
    .Raw
    -0.06
     вида
    -0.06
    acion
    -0.06
    eksiyon
    -0.06
    POSITIVE LOGITS
    amount
    0.07
     eth
    0.07
     regime
    0.07
     grey
    0.06
     solely
    0.06
    68
    0.06
    شي
    0.06
    Sync
    0.06
     bleeding
    0.06
     ψ
    0.06
    Act Density 0.023%

    No Known Activations