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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travels
    -0.08
    -0.08
     viagens
    -0.08
     fierc
    -0.08
    旅行
    -0.07
     vlieg
    -0.07
     Brug
    -0.07
     cobre
    -0.07
    אם
    -0.07
     Rohr
    -0.07
    POSITIVE LOGITS
     Increment
    0.10
    Increment
    0.09
    Adjacent
    0.09
    .increment
    0.09
    _increment
    0.08
     increment
    0.08
     علی
    0.08
     actualización
    0.08
     Aktual
    0.08
    increment
    0.08
    Act Density 0.046%
    No Known Activations